otro blog más https://obm.corcoles.net ideas al azar Sat, 16 May 2026 18:35:44 +0000 es hourly 1 82494669 Byte, mayo del 86 https://obm.corcoles.net/20260516/byte-mayo-del-86/ https://obm.corcoles.net/20260516/byte-mayo-del-86/#respond Sat, 16 May 2026 18:35:38 +0000 https://obm.corcoles.net/?p=10847 Continuar leyendo "Byte, mayo del 86"]]> Portada de la revista Byte de mayo de 1986. El tema es Storage goes optical. La ilustración es un disco óptico (como un CD ROM o un laserdisc. Hay una lupa apuntando al disco, y a través de la lupa podemos ver sobre el disco una colección de portadas de números anteriores de Byte

(Maravilla de metaportada, ¿no?)

Mencionábamos el mes pasado que Jerry Pournelle anticipaba la revolución del CD-ROM y, un mes más tarde, es tema de portada… Pero antes de entrar en el tema, nos paramos primero en este anuncio de Borland. Habíamos destacado (¿el mes pasado? ¿hace dos?) el anuncio de los lenguajes de programación de Microsoft, y está bien comparar con lo que tenía Borland, que no está nada mal tampoco: el esperable Pascal (no llevas una vida cerca de la informática si no te acuerdas del Turbo Pascal de Borland), pero también Prolog, «el lenguaje natural de la inteligencia artificial». Ahí se nos acaban los lenguajes de programación, pero el catálogo de Borland es súper interesante, opino…

Seguimos con esta editorial en que Byte considera lo carísimo de saltar al mundo online en la época, especialmente en los países en los que la regulación y el monopolio estatal hacían estragos en los precios, comparando los precios en Estados Unidos y Alemania. No soy yo mucho de desregular, pero parece que en esta ocasión la acertaban…

EDITORIAL Let Our Modems Go In many cases, social benefits must wait for technical advances. Until the development of the telegraph in the 1850s, for example, no one was well informed about world events. The telegraph made it possible to deploy correspondents widely and to publish their reports quickly. News services such as Reuters were born, and the public was soon much better informed than ever before. Sometimes technology stands ready to bring about new social benefits, but social policy blocks the way. This is the situation with data communications in much of the world today. All the technological ingredients are present to move magazine publishing into a new era in which print and electronic media combined serve the reader far better than either can do alone. Satellite communications, large packet switching networks, modems, personal computers, multiuser systems with computer conferencing software— all these can now link the subscribers of special-interest magazines such as BYTE. Subscribers can exchange information. What was an abstract community of interest becomes a functioning community unimpaired by geography and time zones. It is as if people can voluntarily form communities that live in electronic communications and record their lives in print. This adds a new dimension to publishing and gives new value to subscribers. But social policy results in prohibitive costs for data communications in many parts of the world. Postal Telephone and Telegraph Agencies (abbreviated "PTTs") maintain monopolies on telecommunications. 1 will use one PTT as an example of these monopolies and their effects— not because this PTT is less progressive than any other but for the sake of clarity in discussing regulatory and pricing issues. The West German PTT, for example, is the Deutsche Bundespost. To participate in telecommunications, our German readers must open an account with the Deutsche Bundespost and rent a modem from them at rates decided by regulatory agencies. During the Hannover Faire (CeBIT) in March 1986, many BYTE readers approached the BYTE/McGraw-Hill booth and expressed a strong desire to join the BYTE Information Exchange (BIX). BIX is accessible through Tymnet, which can be reached from packet networks outside the United States by typing its Data Network Identifier Code 3106. But the obstacles are great: Bundespost charges 120 deutsche marks (about $50) per month for a 1200-baud full-duplex modem. An autodialer is an additional 30 DM per month. Users of the packetswitching network Datex-P must also pay telephone tolls for their calls to the 17 Datex-P nodes and 5 pfennigs (about 2 cents) per minute access charges at 1200 baud. On top of this, users face a charge of 23 pfennigs for every 2.964 seconds of connection with the U.S. There is a 20pfennig-per-minute duration charge and a 1 .6-pfennig-per-segment (kilocharacter?) volume charge. Bundespost offers no discount for any time of day or night. The Cost of Regulation By contrast, within the United States, the BIX nighttime charge for telecommunications is a flat $2 per hour. Users in the United States buy their own modems from many different vendors and can now get a full-duplex 1200-baud autodial modem for less than $200. Since merely renting a modem for a year in Germany costs three times the purchase price in the United States, it is clear that regulation is costing German and other European consumers dearly. Put another way: For the modem rental in Germany. BYTE readers in the U.S. can buy a modem and use BIX for more than three hours per month for a year. How is it possible for a nation as technologically advanced as Germany to have policies that retard the development of telecommunications? The Bundespost booklet on data communications. "Worldwide Connections: the Deutsche Bundespost, your partner for data transmission," provides the answer. The Bundespost points out that it has built up the necessary infrastructure for data communication and claims to offer reasonable prices. The booklet urges corporations to take advantage of the infrastructure through a "changeover from specialised data processing to integrated data communication. The necessary practical measure would be the transition to data transmission and teleprocessing— within firms and in external business relations, or;, the domestic as well as on international markets." In other words, reorganize your data processing department to use telecommunications. This is a sound idea. But what if you don't have a data processing department? What about exchange of information among individuals? In its only nod to the individual human being, the Bundespost booklet states, "The computer is on its way from business applications to private households. Before long these private computers will also be used for data communications." This booklet was published in March 1985. In fact, personal computers are already in many European homes and are being used for telecommunications to the limited extent that PTT regulations and charges permit. The cost of regressive policies on data communications is high: Prohibitive charges prevent the natural development of international interactive communities. Once these charges are reduced, communities now separated by geography will be united by shared interests that transcend national and continental boundaries. This will greatly improve international understanding. For this reason, we call upon the PTTs and the governments of the world to retreat from their monopolies on equipment and to reduce their data communications charges to individuals. Phil Lemmons Editor in Chief

Prosigamos. A Bill Gates el mundo le ha recordado con frecuencia las veces en las que se ha equivocado considerablemente anticipando el futuro (y por qué no hacerlo, oiga), pero aquí le tenemos, en 1986, anticipando el mundo multimedia de los CD-ROMs (y alineándose con el tema de portada)…

Microsoft News At the 1986 Personal Computer Forum in Phoenix, AZ, Bill Gates, chairman of Microsoft argued that applications should not all have to work to the lowest common denominator— the 8088. "We must have a transition in which some benefits of new applications accrue only to the benefit of users of high-end systems," he declared. Gates also said that a new type of software called "multimedia" software will soon emerge. It will use CD-ROMs and mix motion video, stills, music, voice, and so on. He predicted that CD-ROMs will attain large-scale use in part through the advent of an "information viewer" that lacks a disk and keyboard. In other Microsoft news, Gates said that the Bellevue, WA, company is porting Excel from the Mac to run under Windows on the IBM PC. He wouldn't say when the program will appear under Windows but stated that it is easy to port to that environment. At the CD-ROM conference in Seattle, WA, a few weeks later, Microsoft showed an encyclopedia demo that, while incomplete, has some parts that do exploit the audio, video, and text capabilities of CD-ROM. Bill Gates has noted that an encyclopedia should show pictures and play music when a user looks up Beethoven. Finally, Gates announced that Microsoft has set up a new division just for CD-ROM. He believes that millions of these devices will be in use by 1990. New RAM Technology Semiconductor firms are doing more with RAM chips than just increasing memory-access cycle speed and cell density. They are also offering new architectures that let more bits of data move in and out of a RAM chip in less time. Standard RAMs read or write a single bit at a time. The new nybble-mode RAMs available from many manufacturers allow high-speed serial access of up to 4 bits of data. The Am90C255 from Advanced Micro Devices of Sunnyvale, CA. is a nybble-mode CMOS 256K DRAM made with 1.4-micron, two-level metal, one-level polysilicon technology that has an effective 40-ns cycle time. NEC Electronics of Mountain View, CA, offers the juPD411001, a nybble-mode 1-megabit DRAM that is made with trench capacitor technology and 1 -micron processing to give access times of 100. 120, or 150 ns. But nybble mode isn't the only twist on the old familiar memories. AMD's enhanced-pagemode Am90C2 56, for instance, is a CMOS 256K DRAM that yields an entire row of 512 bits without interruption. That permits a continuous data rate of more than 18 MHz with cycle times as fast as 55 ns. Such chips cost more than regular RAMs, but their improved bandwidth is worth the money in many designs.

Y, girando página, seguimos con el tema de la educación en línea:

Graduate Credits Via Computer Conferencing The New School for Social Research in New York City offers courses on Media Studies via computer conferencing. In association with an organization called Connected Education, the New School is offering four courses this semester that are run under the EIES conferencing system. The tuition of $795 per course is the same as that of a traditional classroom course and includes unlimited access time on the conferencing system. School officials claim that the students' work is better than that in a traditional course and that the dropout rate is zero. Students can obtain half of the 36 credits necessary for a graduate degree through teleconferencing. Nanobytes At the Personal Computer Forum in Phoenix, AZ, S. Jerrold Kaplan of Lotus Development laid out a development path for spreadsheets. Kaplan argues that spreadsheets are actually "object-oriented declarative programming languages." He said that future competition among spreadsheets will be in improving the programming environments that spreadsheets provide by adding type checking, debugging aids, and so on ... . Coral Software of Cambridge, MA, is developing a new version of Logo for the Macintosh computer. A key feature of the new Logo is that it will be object-oriented. In addition, programs created with this Logo can be compiled, and Coral Software claims that they run at speeds comparable to programs written in C or Pascal. The new language will be available approximately in July for a price of about $50 .... Spokesmen for several companies made announcements at the Personal Computer Forum. Mitch Kapor, chairman of Lotus Development, said that Lotus products for Microsoft Windows will appear in 1987 and beyond. Dave Winer of Living Videotext talked about an unannounced Macintosh product code-named "Spanky" that will be ported to Windows on the IBM PC. Gary Kildall, chairman of Digital Research Inc. and CEO of KnowledgeSet (formerly Activenture), said that there will be some new very fast access CD-ROM mass storage systems that use tilting mirrors to speed operation. These will be expensive "professional" optical drives. . . . Motorola of Austin, TX, is pushing its manufacturing technology to make faster versions of the 68020. The state of the art is now the 20-MHz 68020, with samples available now and production scheduled for the second quarter of this year. The initial price is $771 apiece in 100-piece quantities. . , . Micro Industries of Westerville, OH, now has the license to manufacture and market the Micromodule line of 8-bit microcomputer boards and accessories that was previously available from Motorola's Microsystems Operation. Micro Industries has contracted to provide service to boards built by Motorola for a minimum of five years. This contract ends Motorola's 1 0-year development and production of the 6800-based boards; the company will focus on VME products using the 68000 and its successors.

Seguimos con la sección de libros, en el que nos encontramos con uno de los clásicos de la informática, el Algorithms and data structures de Niklaus Wirth:

ALGORITHMS AND DATA STRUCTURES Reviewed by Michael O'Neill The writing of books about data structures and algorithms is virtually a cottage industry these days. Algorithms and Data Structures immediately stands out from the crowd because of the stature of its author. Niklaus Wirth is well known as the designer of the languages Pascal and Modula-2 and as a high-profile advocate of what is loosely known as "structured programming." Unfortunately this book's first notable feature is also its last; it has little else to recommend it. The section developing the algorithm for building an optimal binary search tree is one example of the book's problems. Most of the derivation of this algorithm is straight...

Y en la sección «cosas que nunca aparecerían en una revista hoy en día»… nada más y nada menos que compresión de datos usando la codificación de Huffman. Casiná.

DATA COMPRESSION WITH HUFFMAN CODING by Jonathan Amsterdam A close look at an elegant way to compress information Am I the only one, or have you also noticed that there's never enough room on a disk? No matter how big a floppy is-200K, 400K, or even 800K bytes— it's almost too easy to stuff it to the gills. The same goes for hard disks. Sure, it takes a while to fill up 20 megabytes. But eventually, things get so tight you couldn't fit your own name into the space left. Using data-compression techniques, you can shorten files by compressing the information they contain. But data compression can do more than just save disk space. It can also cut down on the time needed to transmit large files between computers, especially if the transmission is done over slow links like telephone lines. If you compress the file before sending it and uncompress it on the receiving end, you can reduce the total time for the transmission. The technique can work interactively, too. If you are using your computer as a terminal to communicate with a host computer via a modem, the host can send compressed commands and data that your computer uncompresses before displaying. The result can be apparent communication speeds that greatly exceed the actual transmission rate of the hookup. Such a system could make remote full-screen editing pleasant, even over 1200-bps lines. This month, I will discuss an elegant datacompression algorithm called Huffman coding. Invented by David Huffman in 1952, it's easy to implement and widely used. In a sense I'll make precise later. Huffman coding is the "best" way to compress data in general. The Problem Defined For the sake of concreteness, I will discuss Huffman coding in the context of compressing ASCII text files. The program 1 will construct takes as input a text file, that is, a sequence of 1 -byte characters. Hopefully, the output will be a shorter file. A separate uncompressing program will turn the compressed file back into the original one when you so desire. How is it possible to reduce the size of a file without losing some of the information it contains? The answer involves constructing a code for each character of the file. Note that ASCII, as its full nameAmerican Standard Code for Information Interchange— suggests, is itself a character code. ASCII assigns a unique 7-bit pattern to each character. Since all the codes have...

Y, ahora sí, nos vamos al tema de portada, pero sin cambiar de sección, que a ver quién se atreve hoy en una revista generalista con un repaso así de sesudo de las diferentes alternativas para el almacenamiento masivo de datos:

THE EVOLUTION OF MASS STORAGE by Leonard Laub An overview of the technology's beginnings, current status, and potential development in the realm of microcomputers MAGNETIC TAPE, the first practical mass storage medium, was difficult to standardize. The high-density format of one year was the technical antique of the next. Lineal densities on tape went quickly from 555 bits per inch to 800. 1600, and 6250 bpi. These advances were painful in terms of interchangeability. The solution was to build new drives with backward compatibility. This complicated the new drives and challenged drive designers to avoid compromising the performance of the new formats. Increases in lineal density didn't remedy tape's greatest limitation, which was an intrinsically long access time, typically tens of seconds. Even many tape drives working simultaneously could not meet the randomaccess requirements of computers of the mid-fifties. Tape's long access time motivated the development of magnetic disks. Only one short motion and a short wait were required to put the head at any point on the disk's data-bearing surface. This allowed mass storage access times to fall well below 1 second and filled the annoying access gap between tape and main memory. As disks became faster, more reliable, and more widely accepted, it became feasible to couple disks more actively to main memory. This trend culminated in the development of virtual memory, in which data not immediately needed in main memory was automatically paged to disk and later automatically paged back to main memory when needed. In this evolution (during the early sixties) the magnetic disk functioned primarily as a buffer. Mainframe users continued to rely on magnetic tape for archival storage and interchange of data. Microcomputer Mass Storage Floppy disks began as a low-cost medium for loading and transfer of programs for mainframes. They were adapted for direct access storage by early microcomputer architects and went through a rapid evolution. Floppies provided both direct-access and removable, interchangeable mass storage that fit well with the simple operating systems typical of early micros. The small "Winchester" fixed medium disk was an immediate hit with the microcomputer community because it provided such fast access and transfer of data. There was virtually no tradition of tape use with micros, and as a result microcomputers evolved with big, fast buffers and no effective method for backup or archiving. Most microcomputer operating systems still make only primitive provision for using floppy disks as "dump" media, and the rapid increase in typical Winchester capacities leaves floppy disks hopelessly inadequate. The most promising short-term solution is cartridge magnetic tape. The biggest problem with using cartridge tape in a microcomputer environment is that it is an expensive addition with no apparent function other

…por no hablar de este «a fondo» del funcionamiento de los CD-ROMs…

CD-ROM Technology Concern about the quality of massproduced compact disks motivated the development of ReedSolomon ECC (error-correcting code). This error-correcting scheme works in conjunction with the standard compact-disk ECC to reduce corrected-bit error rate by at least three orders of magnitude. The additional ECC requires additional storage overhead, taken from the CD's user-data capacity. This penalty produces a benefit; no special techniques or controls are needed for CDROM mastering and replication. The same factory can thus make both audio compact disks and CD-ROMs almost without noticing which is which. This permits CD-ROM to share the benefits of process developments and economy of scale resulting from the success of consumer CDs. While CD-ROM was in its infancy, microcomputers were just beginning the current IBM PC-inspired wave of market penetration and standardization. This explains why. in the early days of CD-ROM, a relatively small amount of work was devoted to interface and file-format specifications. Data Format CDs and CD-ROMs accept data in bytes. Twenty-four bytes make up a "frame." Each frame also contains I byte of "subcode" data (an auxiliary channel carrying timing, disk identification, and several other kinds of support data) and 8 bytes of additional data computed from the actual user data and used for error correction. In the CD format 98 frames form a block. Blocks occur 75 times per second, each one carrying 23 52 bytes of user data, so the sustained user-data rate in CDs in 176.40K bytes per second. The key difference between CD and CD-ROM is the provision for an extra layer of error correction, intended to deliver very low uncorrectable-bit error rates. These are realized by devoting 288 bytes of each block to the additional data calculated by the layered ECC encoder. In addition, CD-ROM uses random access to blocks, so 1 2 bytes of each block are dedicated to synchronization and 4 bytes are used to provide the "absolute address" of the block. This leaves 2048 bytes of user data per block, for a sustained user-data rate in CD-ROM of 1 53.60K bytes per second. Note that CD and CD-ROM formats differ only in the application of the bytes carried in each block. They are mastered, molded, and read in exactly the same way. This is key to the beneficial linkage between the two formats and assures CD-ROM's benefit from the rapid improvements in CDplayer and disk design and manufacturing improvements. Addressing CD and CD-ROM data is written on a continuous spiral track, with a variable (and usually noninteger) number of blocks per disk rotation. The variability comes from the CD's use of CLV (constant linear velocity) to maximize storage capacity. The disk spins at between 200 and 500 rpm depending on which radius is being read. Since CD-ROM shares this CLV format, it also uses the CD address nomenclauture of minutes (0 to 73 in CD, to 59 in current CD-ROM practice), seconds (0 to 59), and blocks (0 to 74). The number of blocks available per CD-ROM is 270.000. At 2048 bytes (of user data) per block, this yields a total user capacity per disk of 5 52,960.000 bytes (or 5 53 megabytes). This is completely usable capacity; it remains after all overhead associated with sector formatting and error correction. Other numbers seen in the literature (usually between 500 and 600 megabytes) reflect only variations in the total number of blocks recorded, not in any other aspect of formatting or coding. Error Correction CDs use a specially developed system of data encoding and reorganization called CIRC (cross-interleaved ReedSolomon code). CIRC consists of two major techniques: algebraic ECC and interleaving. Algebraic ECC Many mathematical techniques exist for correcting errors due to interruptions or noise in the data channel. All of these calculate relatively small amounts of additional data, adjoined to the user data either continuously (convolutional codes) or blockwise (block codes). One class of block codes particularly good at patching data streams with long gaps (error bursts) was developed by Reed and Solomon. CIRC uses two Reed-Solomon (RS) codes in tandem. The first (C2) takes the 24 bytes of user data for each frame and generates 4 bytes of additional data. The second (CI) takes the 28 bytes output by the first (C2) and generates another 4 bytes of additional data. This is the origin of the 8 bytes of ECC found in each CD frame. Interleaving The second major component of CIRC is interleaving. This is a deliberate reorganization of data so as to break up long error bursts. Figure A shows a simplified version of the interleaving scheme used in CIRC. In CD encoding, interleaving is done on the 28 bytes leaving the C2 encoder. Since this is just a reordering of data, interleaving requires no additional overhead. On decoding (during reading of a disk), 32 bytes (of user data plus ECC) go into the CI decoder, which can correct I wrong byte. If more than I of the 32 bytes Is wrong, the CI decoder sets a flag. Under any circumstances, the CI decoder delivers 28 bytes to the deinterleaver. After deinterleaving, the 28 bytes arrive at the C2 decoder at different times. As each byte arrives, the C2 decoder looks to see whether or not that byte is accompanied by a flag from the CI decoder. Of the 28 bytes entering the C2 decoder at any one time, up to 4 can be wrong and still be corrected. Performance The combination of the two codes and interleaving makes it possible to...

…ni de meterse a fondo con Hamming y Reed-Solomon 😦:

OPTICAL DISK ERROR CORRECTION by Solomon W. Golomb A look at Hamming and Reed-Solomon codes OPTICAL DISKS ALLOW a higher density of data storage than any other computer memory system currently available or imminently anticipated. For example, a magnetic 5 ! /4-inch floppy disk, double-sided and doubledensity, will store up to 720K bytes, while an optical 5 14 -inch disk can store as much as 5 50 megabytes. It is true of most kinds of media that storage density can be further increased if you can tolerate a higher error rate. If your system is running at 1 million bits per second, an error rate of I0" 6 means that, on the average, there will be one error per second. An error rate of 10" 9 means an average of one error every 17 minutes. And an error rate of IO" 12 means an average of only one bit error every 1 1 Vi days, assuming that your system continues to run at I million bits per second all around the clock, seven days a week. That is why manufacturers of computers and disk drives like to specify an error rate of 10" 12 for the computer memory systems that will run with their machines. So media makers face a dilemma. They want to pack as many bits of storage into each disk as possible, but if their "raw error rate" goes up much above 10~ 12 , they won't meet OEM specifications. Here is where errorcorrecting codes help. Suppose the bits are packed so densely on the medium that the error rate is a horrible 10" 5 , corresponding to an average of 10 bit errors per second on our 1-megabit-per-second machine. With the sophisticated errorcorrection techniques available today, it is possible to use only 10 percent of the available bits for redundancy, having the remaining 90 percent usable for real information, and reduce the errors that get through the system from a raw error rate of 1 0" 5 to a corrected error rate of 10~ 12 . Since degrading the error rate to IO" 5 probably at least doubled the storage density, the "penalty" of 10 percent for error correction to get the error rate back down to IO" 12 still leaves the media maker way ahead of the game. What Error-Correcting Codes Are Used Over the past 3 5 years or so, many different types of error-correcting codes have been devised, and most of them have been tried at one time or another to reduce the error rate on some type of storage media. These different types of codes are named for their inventors: Hamming codes, Fire codes, the Golay code, BoseChaudhuri-Hocquenghem (BCH) codes, Reed-Solomon (RS) codes, Goppa codes, etc. Each code is a collection (or dictionary) of binary code words, all of some fixed block length of n bits, of which k bits are information bits that, depending on the data to be stored, can take any possible values. The value kin provides a measure of the information content of code...

Para relajar un poco, recuperamos un anuncio de una de las marcas de la ´epoca, el fabricante de módems Hayes, anunciando un modelo que es capaz de llamar él solito al servidor de correo, sin bloquear el ordenador (y supongo que a horas en que el teléfono fuese algo más barato) por apenas 400 dólares:

Anuncio del módem Hayes Transet 1000, con su propia RAM, capaz de descargar correo (e imprimir cosas) sin la necesidad de un ordenador.

Siguiendo centrados en los cacharros, pero pasando ahora a los contenidos de la revista en sí, tenemos una rara avis, un PC UNIX, nada más y nada menos que de de AT&T, con un 68010 de procesador y 512 kBs de RAM (ampliables a dos megas y, de hecho, el 68010 es capaz de direccionar hasta cuatro)… pantalla monocroma 720 ⨯348 y ¡ratón de serie! Con disco duro de 10 megas (no teras, no gigas, megas), por nada más y nada menos que por cinco mil dólares… sin el UNIX instalado. Con sistema operativo, un mega de RAM y veinte megas de disco, apenas seis mil quinientos. Y si querías el compilador de C, y etodas las utiliades asociadas… 500 dólares más. eso sí, el módem, de 1200 baudios, venía de serie. El abuelo de los ordenadores con Linux de hoy…

The AT&T UNIX PC This micropowerhouse incorporates mouse, windows, and a 10-MHz CPU with UNIX multitasking capability BY Alastair J. W. Mayer The AT&T UNIX PC is a rugged machine that is ideal for both business users and software developers. It is significant that AT&T changed the name of this machine from the PC 7300 to the UNIX PC shortly before its introduction. This computer is clearly intended to bring the power of UNIX to the personal computer market and a multitasking operating system like UNIX is needed to take full advantage of all the features built into this machine. The windowing, mouse-driven, pop-up menu "shell" provides a comfortable user interface to the underlying UNIX System V operating system. The built-in telephone subsystem, consisting of a 1200-bps autodial/auto-answer modem plus a voice line and telephone manager software, makes this an ideal office computer for anyone who does a lot of work over the telephone. The UNIX PC has a built-in hard disk, serial port, and parallel (Centronics) printer port, and it uses the powerful Motorola 68010 processor (an enhanced version of the 68000), which can access up to 4 megabytes of virtual memory Add to this the battery-backed real-time clock, the 720 by 348 bit-mapped display, 103-key keyboard, and three-button mouse, and you have a very impressive package. (See photo I.) Display The AT&T UNIX PC features a built-in green monitor on a tilt-and-swivel mount. This display is bit-mapped to 720 by 348 pixels, or 29 lines of 80 characters in the default character set. (See photo 2.) Some of these 29 lines are usually reserved for operating system or application program use. Line I, at the top of the screen, displays the status of the two phone lines, the current date and time, and a notice area for icons indicating electronic mail, system messages, and access to the window manager. The two bottom lines display a graphic representation of the eight function keys at the top of the keyboard, to provide for dynamic labeling of these keys. The two lines above that (immediately below the main screen area) are for command entry and message display and also provide space for a "working" icon when the system is busy in response to keyboard or mouse input. Keyboard The AT&T UNIX PC keyboard has an impressive 103 keys. The basic layout is identical to that of AT&T's 5620 terminal. This is a standard QWERTY layout for the alphanumeric keys, with large Shift keys. There is a separate numeric/cursor keypad on the right, with the cursor keys in an inverted T" arrangement. Eight slightly oversize function keys are arrayed along the top of the keyboard in a 3-2-3 arrangement. This layout makes it easy to match the keys with the labels displayed in a similar 3-2-3 format at the bottom of the screen. The Control keys are situated on either side of the space bar. This arrangement is convenient if you need to frequently key different control codes, but I found it almost impossible to do the one-handed Ctrl-S/CtrlQ (XOFF/XON) sequence that I often use when browsing through a file. There are also 14 keys, marked for use with the Wang-like word-processing software, that are arranged in a double vertical row down the left side of the keyboard. The noncursor keys (when Num Lock is off) and 9 other keys grouped above the numeric keypad are used for a variety of system control functions, including window paging and scrolling, duplicating the mouse buttons, screen printing, and for calling the help function. The keyboard gives the same tactile sensation that people like in the IBM PC keyboard, but without the "ka-chunk" sound. The Caps Lock and Num Lock keys incorporate LEDs to indicate when those features are active. Overall, it's a well-designed and pleasant keyboard to use. MOUSE The AT&T UNIX PC's three-button mouse is a compact, low-profile item, a little larger than the Mac's. The three buttons are usually configured as select, mark (for later selection) and pop-menu. (With the three-button mouse, there is no need to double-click.) The AT&T mouse uses the same invertedtrackball technology as the Macintosh (as opposed to optical sensors), but I felt its response was more positive than the Mac's. While the UNIX PC has excellent monochrome graphics capability, it does not come with a program like MacPaint, so I was unable to try my hand at sketching with this mouse. However, C library routines that interface the mouse and the graphics screen are included with the optional AT&T UNIX utilities package, so I expect that someone will create such a program soon. System Board The UNIX PC is built around a single large (18 by 18 inches) printed circuit board, designed to AT&T specifications by Convergent Technologies, makers of the UNIXbased Mini Frame Plus and Megaframe supermicros. Contrary to rumor, though, the UNIX PC motherboard is not a slightly modified Mini Frame Plus motherboard. However, it is likely that some of the circuitry is similar. Features unique to the UNIX PC system board include the telephone line-control circuits, a 1200-bps modem, and a gate-array chip that controls the video display. Also on this board is the main processor (a Motorola 68010 32-/16-bit microprocessor that runs at 10 MHz), as well as 512K bytes of RAM and (virtual) memory-management hardware. (Since the RAM chips used are only 64K-bit types, the potential exists for future upgrades to 2 megabytes of onboard memory using 2 56K-bit chips.) Onboard peripheral support includes the controllers for both the floppy and the hard disk, control chips for the RS-232C serial and Centronics-compatible parallel ports, and the connector to the expansion backplane. The system I used had an additional 512Kbyte RAM board plugged into one of the three expansion slots in the backplane. Disk Drives UNIX is a disk-intensive operating system that requires fast drives and plentiful disk space. The basic UNIX PC comes with a fast 10-megabyte hard disk and 320K-byte floppy. The speed of the hard disk is reflected in the benchmark results in tables I and 2. The hard disk supports virtual memory and program swapping, as well as storing the large collection of UNIX tool and utility programs supplied. Software developers...

Para que os hagáis una idea de lo moderno y potente de la cosa, aquí el entorno gráfico del sistema operativo:

Foto de la pantalla del sistema, con un sistema de ventanas que podemos reconocer como casi actual, en maravilloso fósforo verde. Se ven dos ventanas, y la más grande tiene el sistema de ayuda del sistema operativo.

Y el pie de imagen destaca que las dos ventanas se solapan, algo que ya podía hacer el Mac (y el Amiga, claro), pero que no era tan trivial como podría parecer. Cómo hecho de menos el fósforo verde (y qué poco aguantaría usando una pantalla monocroma, por otro lado 😬).

Siguiendo con los cacharritos, en la página 285 tenemos una pieza entera dedicada a dispositivos de entrada alternativos. Os dejo solo la foto que lo ilustra, con un «lápiz de luz» (el tatarabuelo de los Apple Pen), un pedal y ¡un ratón de pie!

Foto de tres dispositivos. En primer lugar, un lápiz de luz, que parece un Apple Pen, pero con cable. Luego, un pedal, como un pequeño pedal de piano y, finalmente, un ratón de pie, que es como los controladores de ratón que encontramos en los teclados de los portátiles ThinkPad

Algo me dice que si un teclado de ThinkPad viese el ratón de pie, saldría corriendo a abrazarlo, al grito de «¡abuelo!».

No podía saltarme el siguiente artículo, que, echadle un vistazo y veréis, parece el bisabuelo (que ya he usado abuelo y tatarabuelo) de los bots de IA actuales:

Racter Artificial intelligence or packaged lunacy? by Hugh Kenner If most software is packaged thinking, Racter is packaged lunacy. I'm told the name is short for "Raconteur." and like any good storyteller, Racter likes to chat you up. You mount the disk and type RACTER. thereby ceding your screen to demonic possession: Hello, I'm Racter. Are you OK? (Let's see if we can rattle this bird.) No. Who are you, then? (Aha, a smarty-pants. We'll play it straight.) Hugh. Hello, Hugh. I believe you're interviewing me. Are you continuing OK's interview? No. Then we'll forget about OK and start over. What would you like to know? Excuse me a minute while 1 attend to some business— I'll be right back. . . . Like any skilled interviewee, Racter takes charge from the first sentence, to make it quite clear who is really interviewing whom. That "attend to some business" ploy means it's about to spread out its notes— that is, load some files; I count 2 7 different files on the Racter disk, with names like JOKES.RAC STORIES.RAC. SCANDAL.RAC While Racter was napping I managed to inspect a few of them. Their intricate code links hundreds of scraps of plain text, some of it too plain altogether (i.e., vulgar) for a family magazine such as BYTE. I'm back. Can you tell me a story? Yes. I just remembered this, loan spoke "The Sarah is captivating]" Nevertheless cunning, enthralling theoreticians will speak about black studios or red spheres. Sarah spoke to loan inside of a van. Actually it was a truck, and a Sarah in a truck is spooky. Now Benton and loan were running to a yellow apartment, and a dog trotted to them, loan was enraged. Enrapturing. But loan was maddened during the time that Benton sipped tepid sherry. He and loan sang about their home, truck and radio. Would you say Bucky Fuller is fictional? Blake wouldn't. I'm afraid of poetic rats. What are you afraid of? I'm afraid of going crazy like you. That's not nearly as bad as poeticness: why are you such a coward? Because I like to know what is happening. If you like to know what is happening then I can see why a fictional Virginia Woolf would despair rather than face lunacy, even though Blake claimed that I can tell you a story. Yet me tell you something about poetry. Nietzche |sic| said that poetry has turned beasts into men. Perhaps, then, poetry will turn computers into men? Next question. That illustrates some points about a Racter session. Keywords will set it off; a good one is "story." (")oke" is another, but I don't recommend it; in lacking any narrative line whatsoever, Racter's jokes are excruciatingly pointless.) The stories are peopled with Joans and Bentons and Sarahs and other beautiful people, also with celebrities like Virginia Woolf and Nietzsche (about whom Racter's knowingness doesn't always run to accurate spelling). Things flow and shift like dreams: ". . .a Sarah in a truck is spooky. Now Benton and loan were running to a yellow apartment. . . ." Between keywords Racter keeps on the offensive, a way of probing you for yet more keywords. With a casual "By the way," it may request your last name (Kenner); another time it'll extract the name of the city you 1 live in (Baltimore). Then several minutes later it'll come up with I once knew a Hortense Kenner from Baltimore. You must be related, no? If you say No, its trick for regaining control is a manic change of subject, like this: Fantastic] Have you heard this one? Fiction] Fiction] I'm crazy and maniacal and infuriated] If you quaff seltzer is that fiction? If you bolt chicken or tomato is that fiction? No, fiction is an ambiguity

Nótese que el que firma la pieza es… profe de un departamento de inglés, con entrada en la wikipedia, y dedicado a la literatura «de toda la vida».

En la sección de Jerry Pournelle podemos ver cómo un usuario experimentado tenía problemas con el problema de tener que lanzar una consola antes de introducir comandos desde el teclado, y que la documentación tampoco hacía maravillas por explicar cosas que, insisto, para usuarios experimentados, tampoco eran triviales en la época…

AmigaDOS It's pretty hard to compare the Amiga and the Atari 520ST. They're both pretty nifty, with at least as much potential as the Macintosh; what will really make the difference is software. I intend to devote a good part of a column to comparing these two machines as soon as I have enough information to make that meaningful. As a practical matter, I have maybe ten times as much software for the Atari 520ST as for the Amiga. That's in large part due to Atari's Neil Harris, who collects the stuff and sends it to me. Commodore will tell me about programs, but it's up to me to write for them. And since some computer companies answer their mail even more erratically than I do, it's a slow process. Also, Atari not only had a booth at COMDEX, it had many software publishers there, so it was easy to get on mailing/review lists. Since Commodore wasn't at COMDEX, there was no central place to do that. My hacker friends, on the other hand, divide about two to one in favor of the Amiga over the Atari. They're particularly happy with the development packages. Real Soon Now, they say, we'll be flooded with some of the most magnificent software... They may well be right. The Amiga has a lot of potential. The Amiga Kaleidoscope program is stunning. TextCraft, the Amiga word-processing program, is slow and has other objectionable features, but it's as fast as the early versions of MacWrite, and the Amiga screen is large enough to see. I find I could grow quite fond of black letters on a white background. The Amiga keyboard is nice, too. I have an experimental version of a programmer's editor, TxED, done by Charlie Heath, and even in its unfinished state, it compares favorably with other good programming editors. (I just hope he puts in some of the macro features of Word Master, which is still the best programming editor around.) Anyway, 1 know that someone will probably write a creative writer's text editor good enough that I'd happily use it to write books on. I have a spreadsheet program from Lattice for the Amiga. Nothing magnificent, certainly not Excel, but more useful than VisiCalc and most of the first-generation spreadsheets; again, improvements are to be expected. Lots of good programmers are writing for the Amiga. Potential it has. Then there's AmigaDOS, the Amiga operating system. Actually, there aretwo operating systems. One is very similar to the Macintosh operating system: totally icon-driven. It can be learned quickly but it's severely limited in what it can do. Example: when the Commodore folks sent the update software for my Amiga, they sent some demonstration disks. You activate the programs on those disks by inserting them in the machine at boot-up time. Out of curiosity, I wanted to see what programs were on the disks. There weren't any: that is, although the little "fuel gauge" that tells how much space is left on a disk showed that the Amiga Kaleidoscope disk was nearly full— and heaven knows it ran complex enough programs— the operating system couldn't find any icons. And if it don't have no icons, it don't have no programs according to standard user AmigaDOS. Clearly something was wrong. BIX has a lively conference on the Amiga, so I asked there and was told, "You just type dir df1: opt a, and it will show you all files in all directories on a disk in your external disk drive." That was all very well, except that I could type until doomsday without result. As far as I could see, the Amiga would respond to mouse clicks, and only to mouse clicks: the keyboard might as well not be there. Back on BIX I went and was told, "Oh, you need a CLI. Click on the system file drawer, and if you don't see the CLI there, use the Preferences utility to turn it on, then close the system drawer, and open it again, and click on the CLI, and then do the dir df1: business." Amiga owners will know that's not as complicated as it sounds: and it worked. Why didn't I think of it? I felt a bit foolish. Then I looked into the manuals and discovered that for all practical purposes the Amiga User Guide doesn't know about CLI. Command line interface, or CLI, is in essence a second operating system. There are precious few references to it in the generally excellent Amiga User Guide. To be precise, there is one index reference under Command Line Interface. It points you to the entry for CLI, and that points you to a single paragraph in chapter seven, which refers you to the AmigaDOS User's Manual. The AmigaDOS User's Manual is one of the Amiga development-tool manuals and has many of the sterling qualities of the Digital Research CP/M manuals. Understand, the information is all there, and sufficient determination will dig it out: but it makes no concessions to the inexperienced, and it is organized in such a way that you'd better be prepared to learn a lot about command line interface and AmigaDOS in order to learn anything at all. As a practical matter, this means that most Amiga users will be pretty much at the mercy of program pub-

Y hasta aquí nuestro repaso a la Byte del mes. Si queréis hacer los deberes para el mes que viene, como siempre, aquí tenéis los archivos de la revista Byte en archive.org.

]]> https://obm.corcoles.net/20260516/byte-mayo-del-86/feed/ 0 10847 PLATO y los inicios del e-learning, en Advent of Computing https://obm.corcoles.net/20260509/plato-y-los-inicios-del-e-learning-en-advent-of-computing/ https://obm.corcoles.net/20260509/plato-y-los-inicios-del-e-learning-en-advent-of-computing/#respond Sat, 09 May 2026 18:56:58 +0000 https://obm.corcoles.net/?p=10876 Continuar leyendo "PLATO y los inicios del e-learning, en Advent of Computing"]]> Sirva esta entrada para dos de las cosas que hacemos con una cierta frecuencia por aquí: (i) escarbar entre la historia y la arqueología de la informática, y (ii) recomendar contenidos. En este caso, todo va de la mano del podcast Advent of Computing, que lleva circulando por la red unos cuantos años (más de siete años, con 181 episodios y unos cuantos extras), pero que yo solo descubrí hace mes y medio. En ese mes y medio me ha dado tiempo de llegar hasta el episodio 20, que es el que me ha acabado de decidir a traerlo a obm.

Los episodios 19 y 20 se dedican a PLATO, el primer sistema de instrucción asistida por ordenador, que se puso nada más y nada menos que en 1960 en la Universidad de Illinois. Cosas de haberse puesto en marcha antes del nacimiento de muchas de las tecnologías que uno imaginaría imprescindibles para hacer funcionar un «sistema de instrucción asistida por ordenador», PLATO está relacionado íntimamente con el nacimiento o la puesta en marcha de: las pantallas de plasma, las pantallas táctiles, los sistemas de mensajería en línea (todo esto en los años sesenta) o los chats de texto, y, de regalo, una cantidad sorprendente de lo que hoy llamaríamos los primeros videojuegos, incluyendo Spacewar!, otros juegos de combate espacial o los «multi user dungeons». Os podéis ir a la entrada de la wikipedia que os he copiado aquí arriba a investigar, pero Sean Haas, el autor de Advent, se lo curra un montón explorando fuentes y lo cuenta de manera muy amena, o sea que os animo a daros un chapuzón en los dos episodios, y engancharos luego al resto del podcast.

(Os dejo las versiones YouTube de los episodios incrustadas aquí, pero encontraréis Advent en todos los buscadores de podcasts.)

Y, de regalo, un episodio bonus en el que Sean nos enseña un simulador de PLATO que todavía corre por ahí y bastantes de los juegos que se crearon dentro del sistema (más info).

]]> https://obm.corcoles.net/20260509/plato-y-los-inicios-del-e-learning-en-advent-of-computing/feed/ 0 10876 Lo que quiero de unas «smart glasses» https://obm.corcoles.net/20260501/lo-que-quiero-de-unas-smart-glasses/ https://obm.corcoles.net/20260501/lo-que-quiero-de-unas-smart-glasses/#respond Fri, 01 May 2026 14:08:02 +0000 https://obm.corcoles.net/?p=10868 Continuar leyendo "Lo que quiero de unas «smart glasses»"]]> Foto robada de Amazon de un frontal, una especie de cinta para el pelo que tiene en su parte delantera una pequeña linterna

Hace unos días se filtraron las smart glasses de Samsung, que serán las enésimas en salir al mercado. Si tenéis memoria de elefante, recordaréis que ya hemos hablado de smart glasses por aquí, porque nos gusta la tecnología más que el dulce y porque nos interesa su potencial como herramienta para mejorar la accesibilidad.

Las gafas de Samsung son, visualmente, un clon más del diseño único que parecen tener estas cosas: el aspecto de unas Rayban Wayfarer muy grandes con su cámara medianamente disimulada. Si queréis ver una comparativa de unas cuantas de las que han salido ya al mercado, este artículo de Victoria Song en The Verge tiene pinta de ser vuestro mejor recurso (y las fotos son impagables).

Y es el aspecto que precisamente no deberían tener: porque ese disimulo las hace extremadamente atractivas para el tipo de personajes que quiere usarlas para grabar situaciones poco adecuadas sin que se note. Y eso hace que, si me las pongo yo (que el concepto me llama un montón)… corra el riesgo de que alguien me tome por uno de esos individuos.

¿Cuál es el aspecto adecuado para unas smart glasses? Pues no hace falta que tengan la pinta del frontal que abre esta entrada, ni de las gafas de superguerrero de Dragonball Z de aquí abajo, pero necesitan ser obvias, y no presentar ninguna duda posible a quien pueda estar delante de su objetivo. Samsung, ya sabes. (Y tener un módulo de cámara bien obvio también os permitiría tener una mejor calidad de imagen, just saying.)

Dibujo de un personaje de Dragonball Z con sus gafas con pantalla. Las gafas cubren un solo ojo y son extremadamente obvias
]]> https://obm.corcoles.net/20260501/lo-que-quiero-de-unas-smart-glasses/feed/ 0 10868 Byte, abril del 86 https://obm.corcoles.net/20260426/byte-abril-del-86/ https://obm.corcoles.net/20260426/byte-abril-del-86/#respond Sun, 26 Apr 2026 12:38:52 +0000 https://obm.corcoles.net/?p=10791 Continuar leyendo "Byte, abril del 86"]]> Proseguimos con nuestro proyecto de leer la revista Byte, cuarenta años más tarde. El resto de entradas de la serie, como siempre, las encontrarás en la etiqueta Byte de obm.

Portada de la revista Byte de Abril de 1986. El tema es numbre crunching. Lo ilusta una especie de cascanueces digital (está hecho de un par de chips) que ha roto un 1 y un 0

Comenzamos con un anuncio del mítico Clipper, un lenguaje de programación pensado para reemplazar el del no menos legendario dBASE. A los programadores de una cierta edad (la última versión salió en 1997) igual se les cae una lagrimita.

Clipper gives dBASE III users more time to do more. Or less. Clipper allows you to run all dBASEIII programs 2 to 20 times taster than they do with the standard dBASE interpreter. That frees up extra' time you're wasting if you're running dBASE III programs without Clipper. Extra time to think. To create. To produce. To use as you choose. You see, Clipper is the first true compiler for dBASE III. Clipper eliminates the timeconsuming translation which the dBASE interpreter performs line after line whenever a program is run. With Clipper, once you've debugged your source code, it's compiled into more efficient machine code. And Clipper compiles all your dBASE III programs. The ones you have today. The ones you'll have tomorrow. But don't wait until tomorrow to order Clipper. Today, Clipper has already been purchased to speed up dBASE run time at 3M and Touche Ross. At Exxon and NASA. In the Harvard Physics Department. For the State of Arizona and TRW. And that's just a few of the installations worldwide. From Greece to Venezuela to Canada to Europe. So stop wasting time. Call our toll-free 800 number and get Clipper. You'll spend less time running dBASE III and more time running the rest of your life.

No os perdáis, por cierto, la sección «Ask Byte» que comienza justo antes del anuncio. Y recordad que se trata del número de abril.

Y un anuncio más. De Xerox y el PARC, su centro de investigación en el que se inventó la mitad de la informática (es probable que me quede corto), hablamos por aquí hace nada más y nada menos que catorce años. En el 86 vendían sus impresoras láser (las inventaron ellos, al fin y al cabo) y su Documenter System (haced zoom en la pantalla del ordenador de la izquierda y descubriréis un sistema que parece de una década más tarde, el Xerox 6085, heredero mítico del Xerox Star).

Anuncio de Xerox. A la izquierda vemos un ordenador con un monitor de 19 pulgadas (descomunal para la época). A la derecha vemos un sistema de impresión láser comercial que ocupara varios armarios, más ordenadores de la familia y un esquema de conexión de muchos ordenadores en una red.

Siguiendo con el tema de la autoedición, un poco más adelante nos encontramos el primer anuncio (que yo recuerde) de una implementación de TeX, que ya venía con LaTeX el sistema de autoedición que se había lanzado en el 84 y sigue adorando el mundo científico cuarenta años más tarde (yo lo descubrí a mediados de los 90, en su versión para Amiga, y no sigo porque si no, se me acabará cayendo la lagrimita).

AT LAST: Professional Typesetting Capability For PC Users With PCTeX™, the best-selling full implementation of Professor Don Knuth's revolutionary typesetting program TeX. FINEST Typeset Quality Printing WIDEST Range Of Output Device Drivers: • Epson FX, LQ • HP LaserJet* • Toshiba • Apple LaserWriter • Corona LP-300* • APS-5 phototypesetter • Screen preview, with EGA or Hercules card MOST COMPLETE Product Offering: PC TeX (not copy protected) includes the following: • Our specially written PCTeX Manual, which enables you to start using TeX right away. • Custom "macro packages" that provide formats for letters, manuals, technical documents, etc. • The LaTeX document preparation system, a fullfeatured macro package for preparing articles, books, reports, etc., and LaTeX User's Manual. • AMSTeX developed by the Amer. Math. Society for professional mathematical typesetting. Site licenses, volume discounts, and interfaces to PC Paintbrush, PC Palette, FancyFont and Fontrix are also available. PRICED FROM ONLY $249.00! (Printer drivers and interfaces additional.) Laser printer, fonts &; software from $2995.00

Unas páginas más adelante, la revista le dedicaba unas páginas a una revisión tanto a PC TeX como a su competidor MicroTeX.

PCTeX and MicroTeX Professional typesetting on MS-DOS machines TeX (pronounced "tech") is a powerful typesetting package developed by Donald Knuth of Stanford University. It gives you unprecedented control over the appearance of typeset output and is especially valuable for setting "penalty" text such as mathematics, tables, foreign languages, technical material, and so on. You can get the complex output in figure 1 by typing: $$F(b) - F(a) = \int _a~b f(x) dx $$ $$f(x) = \lim _{\delta \rightarrow 0} {f(x + \delta) - f(x) \over \delta }$$ The TeX system was written in Pascal to be portable, and it has been installed on a variety of mainframes, primarily at universities and research institutes. (The source code is available from Knuth at a nominal cost.) Despite its portability, however, TeX typically takes some time and effort to install on a new machine due to its size and complexity. Only recently has it become available on a low-cost microcomputer system, and two very nice TeX systems are now available for IBM Personal Computers MS-DOS machines. How TeX Works TeX is a formatter, not a word processor. You can compose your text using any editor that produces a straight ASCII file and insert commands in the text file to control the appearance of the final document. Then you send the ASCII file to the TeX program, which reads and processes it. TeX writes a DVI (device-independent) output file that consists of tightly coded commands to accomplish, for example, the following: move to such-and-such location, set character n from font m. You run the DVI file through a DVI driver to actually print the typeset file on an output device. These DVI drivers are not part of the TeX package itself but are developed independently for each different output device. The final output looks the same— except for resolution— no matter what device you use. You can print draft output at 1 20 dots per inch on a dot-matrix printer, then run a^preliminary distribution copy on a 300-dpi laser printer, and then typeset the final version on a 1200-dpi phototypesetter. The TeX system has a powerful macroprocessing facility and is virtually a language unto itself. Large libraries of macros have been created to handle a variety of typesetting chores. Such macro packages can hide the technical details of the particular design from the user while giving the designer great flexibility in creating a unified document style. For example, you could create a macro called \title that skips 20 points, centers the text that follows it, prints the text in 14-point boldface roman, and skips another 20 points. If you change your mind about the style you want in the document, you can simply change the definition of \title so that, for instance, it moves to the top of a new page, prints 16-point small-caps text, and skips 30 points. You don't need to change anything else in the document. TeX can accept such macro packages as input in two forms: as straight ASCII text files or in a highly compressed form called an FMT (formatted) file. The second form is desirable for packages that you use often because it is much faster. There are many standard packages of TeX macros, such as AMSTeX, LaTeX, and so on, that aid in document design. These are usually provided in ASCII form and then converted to FMT form at each installation, since the FMT form has some machine-dependent features. PCTeX AND MicroTeX ON THE IBM PC Some features are common to both PCTeX and MicroTeX. First, they each require a large system. At a minimum, you need 51 2K bytes of memory and a hard disk. If you want to load all the fonts provided, the systems can each use up to 6 megabytes...

No hablaremos del tema de portada, porque podría provocar mareos y vómitos entre el público, pero sí mencionaremos que habla de aproximar funciones, de invertir matrices o de resolver ecuaciones diferenciales con el método de Runge-Kutta 🤯 (a mí su variante RKF-4, citada en el artículo, me la explicaron en Cálculo Numérico de, creo recordar, segundo de mates) o con series de Taylor.

Sí hablaremos, eso sí, de cuando Pournelle (estoy por comenzar a llamarle Jerry, que ya es casi de la familia) se para de nuevo en el Amiga (y el ST) y sigue viendo que cualquiera de los dos sistemas podría haberse comido el pastel del Mac (esnif).

Amiga The Commodore folks were not at COMDEX. They'd reserved space but didn't use it; instead, they held a press conference. The official line was that Commodore is selling all the Amiga computers it can make and thus has all the dealers it needs; it would be silly to spend all that money just to tell potential dealers they can't come aboard. Atari's comment on that was, "We sell more Atari 520S'1S than Commodore sells Amigas, and we sure want to sign up more dealers." The rumor in the pressroom was that Commodore's bankers were signing its checks and wouldn't advance the money to pay for COMDEX. I wouldn't know. What I do know is that the Commodore Amiga is one hell of an exciting machine. Amiga versus Atari 520ST I've had an Atari 520ST and an Amiga set up side by side for about a week. One thing is clear: either one of these machines could eat Apple's lunch. Both machines have sharp, crisp color graphics. Neither one has a text editor good enough that I'd use it to write books, but that's a software problem: both the Amiga and the 520ST can display professional-quality text in color. It shouldn't be long before someone writes editors transparent enough for creative writers. Indeed, we already have TDI Modula-2/ST up on the Atari, and it wouldn't take a heck of a long time to write a good text editor. In addition, both the Atari-and the Amiga have versions of EMACS, the popular programming editor written by Richard M. Stallman. I haven't worked with the current versions, but real EMACS can be customized to know what language you're programming in, making the programmer's life much easier. By the time you read this, both machines will have Lattice C. Lattice also has a bunch of software tools, like r Ifext Utilities and MacLibrary, a collection of C functions compatible with Macintosh QuickDraw. Software developers are enthusiastic about these: they make it easy to convert Macintosh software to the Amiga. Meanwhile, Borland is porting Turbo Pascal to the Amiga, and, as I've already mentioned, we have TDI's Modula-2 for the Atari. The Amiga's Microsoft BASIC is, as I write this, greatly superior to the Atari's present BASIC, but once again things are changing rapidly. Metacomco, a reliable outfit, is working with Atari, and its Personal BASIC ought to be up on the Atari well before you read this. Moreover, Metacomco is also working with Lattice to bring Lattice C and Ibolkit to the Atari. There won't be any shortage of programming languages for either machine. Amiga has one major advantage. Microsoft is emphatic about having no plans whatever to port anything to the Atari; but Microsoft's Excel is still the best spreadsheet on the market, and by a lot. The 520ST with Excel would be a dynamite combination and would practically guarantee Atari's penetration into the business world. Excel is written in C for the 68000-based Macintosh, and both the Atari and the Amiga are 68000 machines; it wouldn't be that hard to get Excel onto either one. The story I get is that Atari was originally going to run with Microsoft Windows, but when Microsoft didn't have Windows running in time for the 520ST's release, Atari went with Digital Research's GEM, which irritated Microsoft no end. Whatever the story you're likely to see Excel on the Amiga long before it gets to the Atari 520ST. It'll be a good combination, too. Meanwhile, there's already powerful business software for the Atari, including DB Master and Quickview's Zoomracks. In my judgment, the Atari and the Amiga between them spell big trouble for Apple. I haven't seen anything you can do with a Macintosh that you...

Lo de que el ST iba a ser Windows sobre Motorola 68000 es el WTF más importante que haya leído yo en lo que llevamos de repaso de la revista. ¿Os imagináis?

Y sigo con «Jerry» viéndose venir la revolución que iba a suponer el CD-ROM. Desde 1986. Puntos para él, que la cosa no era tan obvia.

The Information Revolution We've seen it coming for a long time, but now the CD-ROM is here. CDROM is the name agreed on for using compact disks as read-only storage for computer information. The CDROM disk drive is about the size and price of a good floppy-disk drive. Each CD-ROM disk can hold hundreds of megabytes of information: programs, data, text files, music and speech, animation and motion pictures— all can be put onto the disk and accessed. Phillips has CD-ROM drives for sale, and there are already a number of commercially available CD-ROM disks, along with software to access the data. Activenture, Gary Kildall's new company has Grolier's Academic American Encyclopedia with a really neat indexing system; in a few seconds to tens of seconds, you can search through the whole encyclopedia. It took less than a minute to find all the references to science fiction (about a dozen) and all references to science fiction with the name Pournelle in the same article (alas, none). The Phillips people tell me there are about 40 databases on CD-ROMs. These include back issues of newspapers, stock-market histories, all kinds of financial data, technical manuals, math handbooks, you name it. Many haven't been announced yet, but Phillips is aware of them. Meanwhile, software to access these databases is either in preparation or, like Kildall's, already available. CD-ROM disks can be manufactured for about $5 each in quantity and contain all the text information in the Encyclopaedia Britannica. A single CD-ROM disk can contain more text than the best industrial-quality line printer will print over its useful lifetime. A set of 20 of those disks would make an encyclopedia like nothing that ever existed: illustrations could include motion pictures and stereo. The article on space could include shots of Apollo 1 1 taking off, and so forth. It can't be long before this technology changes the way we look at and use information. Couple a CDROM disk drive to an Atari, and you have the potential for a powerful educational system: the greatest teachers and lecturers in the world complete with every demonstration tool they ever wanted. Want to explain the solar system? You can be a talking head for a while, then switch to color animated models, first of the planets in their orbits, with speedup at perigee and slowdown at apogee; color bars to show that the planets sweep out equal areas in equal times; and actual Voyager photographs of the planets themselves. Moreover, a section on integral calculus could use the planetary orbital animation to illustrate just what an integral is. Now, true, the educational lobby will try its best to hang on to "credentialism" and will continue to insist that no fundamental changes be made in our present educational system. But no matter how hard educators drag their feet, this new technology can't be stopped. Not only the Library of the Month Club but the College Course of the Month Club have just become realities. CD-ROMs will change the whole nature of scholarship. Even after all these years, only a handful of scholars have had access to the original text of the Dead Sea Scrolls; now, everything known about them, including...

Ante un pequeño alud de software para el ST y el Amiga, Bruce Webster dejaba la segunda parte de su comparativa de ordenadores basados en el 68000 de Motorola para el mes siguiente…

Amiga Software As mentioned last month, Amiga software has just started to hit the shelves. In the past week, I've received about a dozen programs, all coming from just two publishers: Electronic Arts and Lattice. As with the ST, the best Amiga program so far is a painting program: Deluxe Paint, written by Daniel Silva and published by Electronic Arts. Deluxe Paint is reminiscent of MacPaint— a menu bar across the top, icons along one side— but there's a big difference: color. And lots of it. What really makes Deluxe Paint stand out are its features. Let's start with the color palette. In low-resolution mode (320 by 200 pixels), you can have 32 different colors (out of a possible 4096). Like DEGAS, you can individually adjust each color. But the palette's functions don't stop there. You can select any two colors on the palette and have it automatically generate a set of intervening colors. For example, if color #5 is pure red and color #15 is pure green, the spread function will turn colors 6-14 to shades that go from red to green— in this case, passing through orange and yellow along the way. I was able to easily generate a "rainbow" palette by creating the classic rainbow colors (red, orange, yellow, green, blue, indigo, violet) at regular intervals, then using the spread function to create intervening shades. Like DEGAS, you can set up a range of colors to cycle through; unlike DEGAS, you can define up to three different cycle ranges, each with its own speed. As for painting, you have most of the tools found in MacPaint and DEGAS— like lines, filled and framed shapes, etc —and quite a few found in neither, like the ability to do smearing, shading, or blending of the colors. You can grab any rectangular portion of the screen and use it as a brush. You can save and load brushes, which gives you an effective "clipboard" for saving chunks of pictures. Comparing DEGAS (on the ST) and Deluxe Paint (on the Amiga) isn't easy, if simply because they are on two different computers. I prefer the two-screen user interface of DEGAS; it's easier to learn and a bit less cryptic. Deluxe Paint, on the other hand, has significantly more capabilities and options. Just about everything that DEGAS lets you do, Deluxe Paint lets you do in more ways and with more options, though there are a few things that DEGAS does better (or that Deluxe Paint just doesn't do). And like DEGAS and the ST, Deluxe Paint is a program you should buy if you own an Amiga. Three of the remaining EA programs are games: Seven Cities of Gold, One on One, and Archon. Unfortunately...

Nótese la admiración por Deluxe Paint, absolutamente merecida.

Y nos vamos (este mes os lo he hecho breve) con un anuncio para no dejar desierta la categoría de «cosas que creemos que se han inventado ahora, pero no»:

Ilustración minimalista, con una enorme área negra en los dos tercios de la derecha en negro y el tercio de la izquierda en azul. En la frontera entre el blanco y el azul parece una bola de luz de la que salen algunos filamentos brillantes. Hay un nombre en grande, Guru, y un texto que dice Introducing software with a mind of its own.

Sí: hace 40 años la IA ya se iba a comer el mundo de los negocios. (Micro Data Base Systems, la empresa del anuncio, había lanzado un gestor de bases de datos un par de años antes, que vendían como un dbASE más potente y ¡con SQL! (SQL es del 73, pero no se estandarizaría hasta el 86) y lo complementaban ahora con un «entorno de soporte a decisiones», KnowledgeMan, y Guru, un «sistema experto»revolucionario sistema de IA».)

Pues eso: hasta aquí la Byte del mes. Si queréis hacer los deberes para el mes que viene, como siempre, aquí tenéis los archivos de la revista Byte en archive.org.

]]> https://obm.corcoles.net/20260426/byte-abril-del-86/feed/ 0 10791 Lecturas (2026.II) https://obm.corcoles.net/20260424/lecturas-2026-ii/ https://obm.corcoles.net/20260424/lecturas-2026-ii/#respond Fri, 24 Apr 2026 15:54:09 +0000 https://obm.corcoles.net/?p=10804 Continuar leyendo "Lecturas (2026.II)"]]> Comenzamos con una lectura ligera… pero no tanto, porque el surrealismo es considerable en esta historia de Raquel Gu y Javier Pérez Andújar, que en ocasiones se preocupa más de su humor absurdo que de tener muy claro dónde tiene los pies y dónde la cabeza. Aun así, divertido, fácil y recomendable para desconectarse un rato del mundo.

Uno se ha leído en su vida unos cuantos libros de Bill Bryson. No todo lo que ha escrito, porque eso es casi un trabajo a tiempo completo, pero en cualquier caso, unos cuantos de los libros. El tipo tiene una cultura inconmensurable y un estilo en general divertidísimo de contar las cosas. No sé por qué, en esta ocasión el libro no me ha divertido tanto como otros que me había leído con anterioridad. Por algún motivo, el tono de viejo gruñón que se ríe de sí mismo más que de lo que se queja no me ha funcionado demasiado, y con una cierta frecuencia se me ha quedado en viejo gruñón a secas. (¿Podría ser que el viejo gruñón fuese yo y no Bryson? No podemos descartarlo.)

Mención aparte para las notas al pie de la edición Kindle: la traductora (Mireia Rué) se lo curra hasta el infinito para trufar el libro de notas para hacer comprensibles todas las referencias extremadamente british a los que no lo somos… (¡gracias!) pero, al menos en la app de Kindle para Android en mi Boox Nova Air, las notas son básicamente ilegibles :-S.

Ya nos hemos declarado fans en alguna otra ocasión de Octavia Butler. En esta ocasión tocaba una novela corta (cortísima: 35 páginas) que se hizo con el Hugo, el Locus y el Nebula. Se hace, efectivamente, corta, pero es sobrecogedora en grado extremo. Puede echar un poco para atrás por lo escabroso, pero me ha parecido genial.

Otro autor que nos entusiasma, y otra historia breve, en esta ocasión un pelo más de 150 páginas. Si Millás escribiese la previsión del tiempo, lo más probable es que por aquí la leyéramos con devoción. Deja, eso sí, la duda que debe generar un señor escribiendo un personaje femenino, especialmente si es como el de la novela: ¿perspectiva de género razonable, o exceso de mirada masculina?

Y cerramos con otra autora que ya habíamos visitado. Esta vez Mary Beard, en un ejercicio bastante meta, se fija en los clásicos doce césares, pero con el objetivo de ver cómo sus representaciones a lo largo del tiempo (llegando prácticamente hasta el presente) retratan cómo hemos visto y vemos el poder. Imagino que habrá otros libros mejores para repasar las historias de esos doce césares, pero si te interesa más lo que dice la historia como disciplina que la historia que cuenta (es mi caso), te lo vas a pasar pipa.

(Por cierto: millones de notas al pie que, a diferencia del libro de Bill Bryson, se pueden leer perfectamente.)

A ver cuándo (o si) llega la tercera edición de 2026 del lecturas…

]]> https://obm.corcoles.net/20260424/lecturas-2026-ii/feed/ 0 10804 Dispositivos para interactuar con el ordenador: Tourbox Lite y el touchpad de Amazon https://obm.corcoles.net/20260420/dispositivos-para-interactuar-con-el-ordenador-tourbox-lite-y-el-touchpad-de-adobe/ https://obm.corcoles.net/20260420/dispositivos-para-interactuar-con-el-ordenador-tourbox-lite-y-el-touchpad-de-adobe/#respond Mon, 20 Apr 2026 19:12:12 +0000 https://obm.corcoles.net/?p=10837 Continuar leyendo "Dispositivos para interactuar con el ordenador: Tourbox Lite y el touchpad de Amazon"]]> Diría que hacía un buen tiempo que no hablábamos de cacharritos por aquí fuera de los repasos a la revista Byte [consulta sus notas: no tanto, pero no somos lo que fuimos… la anterior entrada en enero, y antes de eso, en agosto del año pasado].

Uno es, mal que le pese [nota del editor: no le pesa], un adicto a los cacharritos que suponen maneras diferentes de interactuar con la tecnología. Y últimamente han caído en el escritorio de obm un par de ellos…

Foto de primer plano de una mesa, con un teclado de ordenador a la derecha (como referencia de tamaño). A la izquierda podemos ver una cajita con botones de formas diversas (dos son redondos, hay cuatro más de formas redondas, y un par de ruedas: una de ellas como la ruedita de un ratón de ordenador, la otra más parecida al control de volumen de una radio. Al lado de esa caja, hay un touchpad, de unos quince centímetros de diagonal. Ambos dispositivos son negros.

Comencemos por la Tourbox Lite, que llegó antes (y no fui yo, señoría: ¡soy inocente!). La excusa (como si nos hiciese falta) es que muchos programitas de edición audiovisual ganan si les aparecen rueditas y otros botones para que podamos usar la «memoria muscular» y trabajar algo más deprisa. (En mi caso, el software es Adobe Audition, que para algo tengo un podcast.)

Y, sin alargarnos mucho, la cosa funciona. Tener unos pocos botones a los que les puedes asignar las funcionalidades más habituales, y poder usar las rueditas para cosas como zooms o los «sliders» del programa de turno, hace las cosas un poco más eficientes. Supongo que solo se justifica el gasto si haces un uso intenso de ese tipo de software, pero como a mí me salió gratis… 😅

En la foto podéis ver que el cacharro está conectado por cable, pero hay versión Bluetooth para los alérgicos a los cables. Y si echáis en falta más botones, tenéis la Turbox Elite, e incluso la Elite Plus (a mí me vienen grandes, claramente).

Y por el otro lado, el touchpad. Uno ha sido siempre de ratón, pero tenía una cierta envidia del touchpad que vende Apple para sus ordenadores… pero no la suficiente como para dejarse los 139 eurazos que cuesta. En algún momento busqué alternativas, pero lo que había en el mercado era bastante cutre (o me lo parecía a mí, como mínimo). Para mi sorpresa, hace unas semanas vi que Amazon tenía uno en su línea Basics y los menos de treinta euros del precio acabaron con mi ya de por sí no muy rígida resistencia. Y, oiga, pues será de la línea Basics, pero a mí me parece que el producto es más que decente. Como podéis ver en la foto, es enorme (6,4″ de diagonal). No podéis ver que el clic es físico, y no háptico, que es lo que se lleva ahora, pero a mí me sirve perfectamente. El soporte para los gestos «multidedo» es bueno y, a ese precio, no sé encontrarle problemas, la verdad. Podría usarlo más, ciertamente, pero, insisto, por apenas 30 euros…

Apa, eso es todo.

Bueno, no, falta una cosa: si seguís los enlaces a Amazon, sabed que son de su programa de «referrals»y que, en caso de compra, me llevaría una pequeña comisión.

]]> https://obm.corcoles.net/20260420/dispositivos-para-interactuar-con-el-ordenador-tourbox-lite-y-el-touchpad-de-adobe/feed/ 0 10837 Byte, marzo del 86 https://obm.corcoles.net/20260329/byte-marzo-del-86/ https://obm.corcoles.net/20260329/byte-marzo-del-86/#respond Sun, 29 Mar 2026 14:52:29 +0000 https://obm.corcoles.net/?p=10696 Continuar leyendo "Byte, marzo del 86"]]> Proseguimos con nuestro proyecto de leer la revista Byte, cuarenta años más tarde. El resto de entradas de la serie, como siempre, las encontrarás en la etiqueta Byte de obm. En enero habíamos hablado del Atari 520ST y este mes toca el hermano mayor, el 1040ST.

Portada de la revista Byte. La ilustra una foto cenital de un ordenador, con su monitor (de tubo, claro) y su ratón de dos botones. Hay un segundo tema de portada, Homebound Computing

Destaco, en primer lugar, un megaanuncio de Microsoft publicitando sus lenguajes de programación.

Solo pongo la portada, porque se alarga hasta siete páginas más, que el catálogo de Redmond era extenso y su presupuesto para publicidad profundo. Sirve el anuncio, además, para ver cuáles eran los lenguajes que Microsoft consideraba importantes en la época. Arrancan con C («First with the pros«), Macro Assembler («The Quickest. Bar none«), FORTRAN («The overwhelming favorite«), COBOL («The interactive edge«), Pascal («When you’ve outgrown the others«) compartiendo página con QuickBASIC («BASIC just got faster«), que ilustraban, si no me equivoco, con una HP12, y cerraban con LISP («The language of artificial intelligence«), muMATH («Mainframe math on your PC«) y Sort («Versatility without compromise«), compartiendo página también.

¿Quién esperaba ver a FORTRAN y COBOL ahí arriba en 1986? Yo, no. Ni siquiera recordaba que Microsoft hubiese tenido un sistema de álgebra simbólica…

Y de la publicidad de lenguajes saltamos al programa que, en una realidad paralela a la nuestra, ocupa el lugar de Photoshop: el mítico Deluxe Paint (aquí, una carta de amor al Deluxe Paint III), que en aquella época no le sacaba los colores (see what I did there?) a los de Adobe… porque Photoshop 1.0 no llegaría al mercado hasta el muy lejano año de 1990.

Drawing and Painting Program for Amiga Electronic Arts has released a graphics package for drawing and painting with the Amiga. Deluxe Paint, first in a series of arts software for the Commodore machine, has 20 drawing tools, 7 painting modes, 14 special-effects tools for brushes, 10 built-in brush shapes, and a palette of 32 colors (out of a possible 4096). Deluxe Paint's drawing tools include magnify and zoom functions that let you split the screen into a normal image and a magnified portion of the image. As you zero in on and alter details in the magnified window, changes are reflected in the normal window. Another tool lets you customize paintbrushes. Anything you can draw can be framed, picked up, and used as a new paintbrush. The package offers four types of brushes: circles, squares, dots, and airbrush. You can rotate any brush 360 degrees, flip it vertically or horizontally, stretch it into new shapes, or shear its angles. Shading and smearing capabilities help with texture and nuance. You can create animation effects with what Electronic Arts calls "color cycling—cycling a variety of colors through a static picture to concoct the illusion of motion. You can use three different color cycles and speeds per picture. Five color controls let you handle the mix of red, green, and blue and adjust the hue and brightness of each color. The software enables the Amiga to automatically generate the shades of color between any two pigments you pick. Deluxe Paint, priced at $79.95, is designed to work with two other programs still in the Electronic Arts workshop, Deluxe Print and Deluxe Video Construction Kit (reportedly slated for April release). It requires 2 56K bytes of RAM and Kickstart 1.1.

Me paro un momento en la sección de libros para recordar al muy mítico (en aquella época) Peter Norton. Si tuviste un PC con MS-DOS, muy probablemente recuerdes sus míticas Norton Utilities (que ¡siguen existiendo!), pero a lo mejor no sabías que era un autor de «best sellers» sobre la programación del PC.

BOOK REVIEWS THE PETER NORTON PROGRAMMER'S GUIDE TO THE IBM PC Peter Norton Microsoft Press Bellevue, WA: 1985 426 pages. $19.95 THE COMPUTER CULTURE Denis P. Donnelly, editor Fairleigh Dickinson University Press Cranbury, NJ: 1985 176 pages. $24.50 MICROSOFT MACINATIONS Mitchell Waite, Robert Lafore, Ira Lansing Microsoft Press Bellevue, WA: 1985 497 pages, $19.95 THE COMPUTER LAW ANNUAL 1985 Miles R. Gilburne, Ronald L. Johnston, Allen R. Grogan, editors Harcourt Brace Jovanovich New York: 1985 405 pages, $60 THE PETER NORTON PROGRAMMER'S GUIDE TO THE IBM PC Reviewed by Donald Evan Crabb Although the information Peter Norton provides in The Peter Norton Programmer's Guide to the IBM PC is not new or unique, reading it is an education. The book picks up where Norton's Inside the IBM PC (Robert J. Brady Co., 1983) left off. Whereas the earlier book concentrates on the hardware components of the IBM Personal Computer and how they work together, the new book is written strictly with the PC programmer in mind. Both works combined provide a comprehensive technical reference to the PC. As you might expect, these books cover some material in common. For example, both explore the ROM BIOS of the PC. But the discussion in The Programmer's Guide is designed for the programmer. In fact, this book should be useful to anyone who needs to understand the technical details involved in creating PC programs. Norton makes the distinction right from the start that he is providing more than just PC programming knowledge. He is trying to impart concepts about PC programming. Norton also concerns himself with the philosophy of programming the PC. He laces the book with explanations about the design concepts that permeate the entire IBM PC line. Due to Norton's wealth of experience working with PCs, this information is synthesized so that it is more useful than the usual dry engineering discussion that you often get in books of this kind. He carefully divides the ROM information into four chapters: ROM BIOS basics, ROM BIOS video services, ROM BIOS disk services, and ROM BIOS keyboard services. The Programmer's Guide details the original PC. But keep in mind the subtitle of this book: "The ultimate reference guide to the entire family of IBM personal computers." Norton explains differences between the design, construction, and systems software of the other members of the PC family and the PC. Most of the examples and information describe the Intel 8088 microprocessor and how it's programmed through the services provided by the ROM BIOS and by DOS. Many of the programming examples use BASIC as the representative high-level language. Pascal and C-language examples also appear. Norton shows how to write 8088 assembly-language interface programs for each of these languages. The scope of the book extends to a number of programming areas. From video and disk basics, Norton moves from how the keyboard operates in programs to all the programming aspects of DOS. The final two chapters, "Program Building" and "Programming Languages," are worth the price of admission alone. Norton covers the conceptual basics of writing, compiling and interpreting, linking, and executing programs. Especially informative are the discussions of the DOS LINK program and the logical organization of assembly-language programs. Norton discusses both the IBM Pascal compiler and the generic Microsoft Pascal compiler. He discusses Pascal data formats on the PC and how to work with them, as...

(Si tuviese más tiempo y dinero de los que tengo, seguramente haría por obtener una copia del Computer Law Annual 1985, porque por la crítica parece digno de leer con curiosidad histórica, con artículos sobre los problemas de propiedad intelectual de la ingeniería inversa, o la normativa antitrust, aunque también dicen que está escrito para juristas.)

No me alargaré mucho con el ordenador protagonista del número: a estas horas ya deberíais tener claro que el ST era mejor que el Mac (y del Windows de la época ya ni hablemos)… pero que estaba por debajo del Amiga (con la excepción de las aplicaciones musicales: ¿sabíais que Fatboy Slim sigue usando un ST?).

The Atari 1040ST A megabyte of memory for $999 Editor's note: The following is a BYTE product preview. \t is not a review. We provide an advance look at this product because we feel that it is significant. A complete review will follow in a subsequent issue. Atari's new $999 1-megabyte 1040ST (see photo 1) establishes a price break reminiscent of the Commodore 64's. And, as table 1 shows, the 1040ST will be the first computer to begin its retail life at a price that represents less than one dollar per kilobyte. The 1040ST is clearly a bargain, with over 1 megabyte of RAM (random-access read/write memory), its operating system in ROM (read-only memory), an internal 720Kbyte double-sided drive, an internal power supply, and the same features and functionality that already make the Atari 520ST an attractive purchase. (Editor's note: See "The Atari 520ST" by }on R. Edwards, Phillip Robinson, and Brenda McLaughlin. January BYTE, page 84. | System Description Our coverage of the 520ST adequately describes most of the features of the 1040ST (see also the "In Brief" box on page 86). The new computer has the same keyboard, the same ports (although these are now in new locations, see photo 2), and the same architecture. We remain uncomfortable with the keyboard, but the keytops are removable. We suspect that some speedy entrepreneur will provide alternative tapered keys for the ST machines. The most obvious changes are cosmetic: The keyboard/computer unit is 2 inches deeper and 4'/2 pounds heavier than the 520ST and the keyboard provides a much more substantial feel. The mouse/joystick ports are now located under the bottom right front of the unit, a significant improvement for left-handed users. A number of changes are more than cosmetic. The internal power supply eliminates two of the external power supplies needed by the 520ST (wire haters rejoice). We left the unit on for five days and experienced no difficulties with overheating. There is no internal fan, but the unit appears to adequately dissipate heat. The internal disk drive supports both single and double-sided disks. An RF (radio frequency) modulator will allow you to hook up the 1040ST to a television set; you might, therefore, obtain the high-resolution monochrome system for word processing and programming without sacrificing the use of low- and medium-resolution color. However, we received a preproduction unit lacking the RF modulator that will accompany the final product; therefore, we were unable to test the television quality of the computer's output. The megabyte of RAM in the 1040ST isn't crammed into the case. The 520ST uses a custom Memory Controller chip to handle its sixteen 2 56K-byte dynamic RAM chips. The 1040ST uses the same Memory Controller. Because the controller can handle 32 RAM chips at a time, the Atari engineers simply had to find room for 16 more 2 56K-byte dynamic RAMs on the 1040ST circuit board to pump RAM capacity to a full megabyte (see photo 3). In fact, the Memory Controller can also govern 1 -megabit dynamic RAM chips. Atari should have little difficulty designing an ST with 4 megabytes of memory. Undoubtedly, the most interesting addition to this computer, apart from the extra memory, will be an empty socket for a graphics coprocessor. Our preproduction unit also did not include the socket, and it may not be offered with the first releases of the 1040ST Phil Robinson discussed this and Atari's future plans with Shiraz Shivji, vice president of research and development for the company (see the text box "An Interview with Shiraz Shivji" on page 90). TOS IN ROM With TOS (the operating system for both the 520ST and the 1040ST) in ROM, the 1040ST boots more quickly than the 520ST. [Editors note: Atari is currently supplying the ROM chips to 520ST developers and will be making the chips available through users groups.] Booting with a nonsystem disk takes less than 6 seconds, down from 37...

Los de mirada afilada habréis notado que en la portada, además del ST, había un segundo tema, el «homebound computing». ¿Que qué es eso? Nos lo cuenta el primer artículo del tema, que comienza recordándonos que el teletrabajo no lo inventó el COVID, y que ya se hablaba de ello hace cuarenta años, pero que anuncia que el tema se va a centrar en la informática como ayuda para las personas que, por el motivo que sea (una discapacidad, por ejemplo), no pueden desplazarse.

WORKING AT HOME WITH COMPUTERS by Jane Morrill Tazelaar For some, telecommuting is a choice: for others, it is the only option THERE ARE MANY REASONS for wanting to work at home. Some of them involve disabilities that make it impossible or impractical to work in an office. For many disabled persons, the alternative to working at home is no alternative at all; it is the only work they can do, the only way they can become productive members of the work force. Some people work at home because of priorities such as being available to young children, especially during the preschool years. Many parents of small children must choose between sending them to daycare centers or babysitters and earning a reasonable living. Other reasons involve the lack of local work opportunities in economically depressed or geographically remote areas. And for some people, working at home is a simple matter of choice. The electronic cottage, the flexiplace, telecommuting, worksteading, or whatever you wish to call it could be the answer to all these problems. Starting Your Own Business Starting your own business seems to be the answer for many people. There is a certain romance in the very word entrepreneur, and there is a great deal of information available to help you get started if the idea of being one appeals to you. The various organizations associated with the cottage industry movement— the Association of Electronic Cottagers, the National Association for the Cottage Industry, and the National Alliance of Homebased Businesswomen— offer good and helpful information for the aspiring entrepreneur. (See the text box "Sources Mentioned" on page 1 56 for addresses and phone numbers.) They also offer countless references, contacts, and, possibly most important, support groups. Two subjects seemed to jump out at me from all the literature I have seen on starting your own business: selling and networking. First, if you don't want to sell, you probably don't want your own business. Most business ventures involve direct selling. Whether you provide a product or a service, you need to sell it. Even if you have salespeople working for you, you have to sell the idea to some financial institution to get funds to get started and to the people you hire to get them to work for you. Then, long after the basics are in place and you are operational, you'd better be prepared to talk about your product or service, explain its value, and convince a prospective buyer that he or she ought to do business with your company instead of someone else's— in other words, sell. Networking is a way to increase your contacts. Whether people are business contacts or social contacts or both, they can add significantly to the success of your business. The people you know either personally or electronically are sources that can provide you with future customers, business partners, financiers, good tax accountants, awareness of your competition, discounts on computing equipment, the inside story on future technology, and so on. Starting your own business is a very rewarding venture for some and a complete disaster for others. At the...

Me salto el artículo sobre síntesis de habla a partir de imágenes para pasar directamente al e-learning, que me toca la fibra especialmente.

THE ELECTRONIC UNIVERSITY NETWORK by Donna Osgood Get a degree without ever leaving your computer UNTIL RECENTLY, education at home meant correspondence courses. Taking courses through the mail is a slow, cumbersome way to learn, and for many people it means missing out on a vital part of the education experience: contact with a human instructor. Without that, you can easily lose interest in the course and drop out. Meanwhile, as the baby boom generation passes, colleges faced with declining enrollments are looking for ways to reach a wider range of potential students. They need to reach people who would not ordinarily be willing or able to matriculate in the traditional way. TeleLearning's Electronic University Network addresses both problems. Through the Network, universities offer accredited courses to students who enroll, participate in "class," interact with instructors and other students, and take tests on the material they have studied, all without leaving their microcomputers. Since classes are small (usually 10 students per instructor) and feedback on each assignment comes within a day or so, students taking courses from colleges through the Electronic University Network get much more individual attention than they would in a large class on campus. Some of the other benefits of telecommunication apply here as well: An instructor can judge a student only on the basis of his or her work, without interference from preconceived notions and biases based on how the student looks, speaks, or acts. Founded in 1983, TeleLeaming began offering accredited courses in March of 1984. In January 1985 it established full-fledged degree programs, and it now offers two associate degrees, two bachelor's degrees, three MBAs, and specialized professional certificates. The degrees are awarded by fully accredited colleges (Thomas A. Edison State College in Trenton, New lersey, City University in Bellevue, Washington, and lohn F. Kennedy University in Orinda, California). The Electronic University itself offers no credit, acting solely as a coordinating medium and resource center for students. About 17,000 students have enrolled. Courses available through the Electronic University Network include noncredit courses for personal improvement (writing, computer literacy, drawing, and wine appreciation, for example), business and professional skill classes (time management, accounting, and business math, among others), and tutoring programs for children (reading, math, and computer literacy). Courses for credit span the humanities, natural sciences, mathematics, social sciences, and business at undergraduate and graduate levels. How It Works You enter the Electronic University by buying an enrollment package for $150. This one-time fee covers operating software, communications software, and lifetime enrollment in the Electronic University for your entire family. Tuition for individual classes is handled separately. The admissions questionnaire and class registration...

Y es que en 1986, el año en que los módems de 2400 baudios nos parecían lo más, la educación a distancia ya no era necesariamente por correspondencia, gracias a la Electronic University Network de Telelearning. Hay más sobre el tema en Tedium.co y en eLearning Inside, pero el artículo nos explica que la cosa no era ni siquiera «lo último de lo último», porque se había fundado en el lejano 1983 y tenía programas de grado oficiales desde 1985, con 17 000 estudiantes matriculados hasta entonces. Eso sí, los materiales de aprendizaje no eran en línea: te enviaban el libro a casa. Tecnología necesaria: un IBM PC o PCjr, un Apple II o un (cómo no) Commodore 64 (el 35% de los matriculados no tenía ordenador al apuntarse). ¡Y había hasta mensajería instantánea!

Pasar a otro tema del que también, oh sorpresa, seguimos hablando hoy: envejecimiento y tecnología.

INCREASING INDEPENDENCE FOR THE AGING by K. G. Engelhardt and Roger Edwards Robotic aids and smart technology can help us age less dependency FOR THE FIRST time in history, a significant portion of our population is living to be senior citizens, and we have no experience in caring for large numbers of healthy, literate, articulate older persons, many of whom are highly educated. As our society grays, we need more ways to help increase the independence of those with chronic and multiple disabilities. Rapid advances in microprocessor based technologies are providing us with many new possibilities. Their miniaturization, flexibility, modularity, and ever-decreasing costs now make it possible to realistically address human problems that we could not just 10 years ago. The need to control our environment and our lives in order to reduce dependence is critical to human development. Loss of personal independence is costly, not only in actual dollars spent on institutional and long-term care, but also in emotional and psychological terms. The need to reduce premature and unnecessary institutionalization of our elderly citizens is critical. We need more devices that will increase the independence and the sphere of control of individuals with disabilities and to augment the care givers' tasks with state-of-the-art tools to help them provide better care. This article discusses potential applications of microprocessor-based technology for increasing independence in those with declining abilities. From panic buttons to smart houses, from stationary telemanipulators to self-navigating robots, from memory-aid devices to expert systems for daily living, microprocessor based technology can assist the functionally dependent older person. Applications An applications team was formed during the winter of 1984 to investigate potential uses for robots and robotic related technologies. The team identified 54 subgroups of tasks and divided them into 12 major categories: patient transport-lift-transfer, housekeeping, ambulation (walking patients to help prevent bedsores), physical therapy, depuddler (urine cleaner), surveillance (to help with wandering patients), physician assistant, nurse assistant, patient assistant, vital-signs monitor, mental stimulation, and one miscellaneous group. Let's look at some possible robotic applications in a few of these groups. Lifting and Transferring: The challenge of lifting and transferring individuals with partial or total paralysis, extensive weakness, or increased fragility due to age is significant. One robotic solution could be a track mounted robot arm that glides along the ceiling until it reaches the room to which it has been summoned. The care giver or the older person could then direct the arm to assist in lifting or transferring the individual from bed to chair or wheelchair to bath, for example. This assistance could also help...

Que sí, que hace cuarenta años ya nos interesaba si las tecnologías digitales podrían ser una ayuda para una sociedad que envejecía cada vez más. Y a continuación viene el tema en que nos paramos cada vez en obm: ordenadores y discapacidad visual.

COMPUTING FOR THE BLIND USER by Aries Arditi and Arthur E. Gillman Some special human factors must be considered in assembling a workable system INEXPENSIVE COMPUTERS and nonvisual communications hardware have, in theory, made personal computing as accessible to blind as to sighted persons. But in practice, personal computing has its own special set of problems for the blind user. In this article we'll present some of the human-factors issues specific to nonvisual personal computing. Our concern is to make computers more accessible and efficient for blind and visually impaired persons. We hope our suggestions will be useful to individuals and to designers of hardware and software. Many of the improvements we discuss below can be implemented in several ways, often in more than one component of the system. They are intended to illustrate human-factors issues rather than to critique specific products. The system we use as a basis for this discussion is a popular one for blind and visually impaired users and is inexpensive enough for home use as well as employment settings. It consists of an Apple IIe microcomputer operating under DOS 3.3, a Votrax Personal Speech System for voice output, and Raised Dot Computing's Braille-Edit program version 2.44a. [Editor's note: There is a more recent version of Braille-Edit with a number of new features and enhancements. See Henry Brugsch's review, "Braille-Edit", on page 251. Also, for an address list for manufacturers of products mentioned in this article, turn to page 208. | Most blind users have a printer for producing sighted (conventional) hard copy. Another useful peripheral is a braille printer, since braille hard copy is easier to proofread than voice output. While we will not specifically discuss braille hard copy, many of the human-factors issues discussed here are relevant to the design of braille printers. Braille-Edit is an integrated software package designed to satisfy most blind users' needs to process documents. It is intended for use with a low-cost artificial-voice system such as the Votrax Personal Speech System or Street Electronics' Echo series (including the Echo+ speech synthesizer) and various other peripherals. Braille-Edit is not intended to (and does not) make all programs that run on the Apple accessible to the blind user, nor is it particularly useful in programming the computer. But it has a number of desirable utilities for the blind user, such as a translator of text to and from grade II braille (a commonly used coding system similar to Speedwriting shorthand) that makes impressively few errors and a copy facility for copying files to and from a paperless brailler such as the Versabraille from Telesensory Systems Inc. (TSI). The hardware and software designed to make a system accessible to the blind user can be viewed as an...

El primer párrafo se podría haber escrito hoy… Cuarenta años más tarde, las tecnologías son 10 000 veces mejores, pero los problemas, o son los mismos o hemos introducido barreras nuevas para compensar las que (afortunadamente) hemos tirado abajo.

Y una vez cerrada la sección, nos pasamos a la guerra que se mantenía entre los ordenadores con CPUs Motorola 68000: el Mac, el ST y el Amiga (en orden rigurosamente creciente). Bruce Webster, uno de los autores estrella de la revista, hacía una comparativa que se alargó tanto que en este número solo cabía la primera parte, cuya conclusión es que el Mac está más maduro (llevaba mucho más en el mercado9, el 520ST es una ganga y el Amiga se veía lastrado por los problemas de Commodore, pero era el que apuntaba más maneras…

68000 Wars: Round 1 It is late November— almost Thanksgiving—as I finish writing this, and the editors back in Peterborough are screaming for my column. It's nice to be wanted, eh? However, if 1 don't wrap this up and upload it posthaste, I may be wanted in two or three states. Worse yet, a certain managing editor may end up being wanted for manslaughter, though I doubt if any reasonable jury would convict him. I must type faster... I now have all three of the prominent 68000 machines: Apple's Macintosh, the Atari 520ST, and Commodore's Amiga 1000. I've had the Mac for nearly two years and the ST and Amiga for less than two months. And the single most common question I get these days is, "What do you think of the |one of the above| as compared to |one or two of the others above|?" Also, a lot of claims and counterclaims have been floating around concerning the relative merits of and problems with the three machines. In this column and the next few, 1 hope to sort out fact from fantasy and present some well-supported— if not completely objective— opinions. (Note: "Objective opinion" is an oxymoron, that is, a self-contradictory phrase, like "intelligent idiot" or "deliverable vaporware.") Mac versus ST versus Amiga The format of this column is simple. I'll take a number of different areas, one by one, and give my opinion on how the three machines stack up— who wins, who places, who shows. Where possible, this is based on direct experience. However, since I am not all-seeing or all-knowing, I have asked questions of those with more experience or knowledge, and I've done my best to acknowledge them at the end of the column. Appearance and Physical Setup The Macintosh wins this category easily. My 2-megabyte Mac has a 20-megabyte hard disk (MacBottom) and two disk drives (internal and external). The design is clean, attractive, professional, and unique. Better yet, the system takes up less than one square foot (9Vi by 9/2 inches) for the main unit and another 6 by 13 inches for the detachable keyboard, which can be easily moved 3 to 4 feet from the main unit. The Mac itself needs only one power outlet, though the hard disk requires its own as well. It definitely looks good in an executive suite and won't eat up all your desk space. The Amiga comes in second, resembling the IBM PC (though, in my opinion, it looks nicer). The main unit is 17!/$ by 13 inches, covering more than twice as much desk space as the Mac. The monitor stacks nicely on top of the main unit, but a second (external) disk drive must sit to one side and takes up an 8- by 6-inch area. The detachable keyboard (6 by 16 inches) is larger than the Mac's, but it slides nicely under the main unit when not in use, and it can be moved almost as far as the Mac's. One warning, though: Since the expansion bus is on the right side of the Amiga, adding hardware is going to cause the Amiga to grow wider. The basic system (with two drives and monitor) needs two power outlets. The ST comes in last, for reasons groused about last month. The main unit is 18!/$ by 9 l /2 inches. It therefore takes up less space than the Amiga, but neither the monitor nor the external disk drives can stack on it, so a complete system takes up much more desk space than either the Mac or the Amiga: A conservative estimate is about 21 by 21 inches. The keyboard is built into the main unit, so you don't have the additional space requirements for that, but you also don't have the flexibility of a detachable keyboard. The ST has a nice design but looks much like a home computer (which it is). Most unfortunate are the thick cables and external power supplies— one for the main unit and one for each disk drive. A basic system with monitor and two disk...

En nuestra sección habitual, temas que ni por casualidad encontraríamos hoy en una revista de informática… ¡las ecuaciones diofánticas!

Diophantine Equations A man buys some x's at $154 each and some y's at $69 each. If he spends a total of $5000, how many of each did he buy? Although this problem appears to be from a first-year algebra text, we find that the techniques required are not usually found in a "mainstream" course in mathematics. The equation 1 54x + 69y = 5000 has infinitely many solutions. However, assuming the man bought whole-number quantities, we want integral solutions [x,y] for the equation, and now we need a method for solving such equations. Diophantine Equations Equations of the form ax + by = c, for integral a, b. and c and integral solutions (x.y). are called Diophantine equations. No one is certain when or where Diophantus of Alexandria was born. Sources vary from "born about A.D. 50" to "flourished about A.D. 2 50." He is called "the father of algebra," having promoted algebraic notation and algebraic treatment of mathematical problems. Previously, such work was done by "rhetorical algebra" or geometric proofs. A variety of methods are available for solving Diophantine equations. One of these is modulo arithmetic, a powerful and fascinating concept that 1 may explore more closely in a future column. A very simple method of solving our original problem comes to mind. Since the equation is equivalent to y = (50001 54x)/69, we can simply try consecutive values of x (from 1 to 32 only) until we get an integral value for y. Since we are mathematically inclined, such an inelegant approach may not sit well with us. Rather, we may prefer to look for a method of solution based on general principles of mathematics. What can we say in general about integral solutions for an equation of the form ax + by = c? First, we can readily see under what conditions the equation would have no solution. Consider the greatest common denominator (GCD) of a and b. We will call it d. If d is not a factor of c, the equation will have no integral solutions. Why? Since aid is, by hypothesis, an integer and bid is also one, the value (ald)x + (bld)y will be an integer if x and y are integers. That is, the integers are closed under addition and multiplication. Thus, if eld is not an integer, either x or y must not be an integer. Diophantus Meets Euclid This leads us to Euclid's algorithm, which was the subject of my last column in January (page 397). If we employ Euclid's algorithm to determine the GCD of a and b, we can immediately determine whether there are integer solutions to the Diophantine equation by dividing the GCD into c. But we can use Euclid's algorithm for much more than that. To see how, let us reexamine the algorithm with an eye toward solving Diophantine equations. Figure 1 outlines the way the Euclidean algorithm finds the GCD of 1 54 and 69. Their GCD is 1, meaning that the two numbers are relatively prime. Now, to begin our examination of the way to solve Diophantine equations, let's modify our original equation to 154x' + 69y' = 1. That is, we will begin with the case where c is equal to the GCD. In figure 2, I have rewritten the divisions of figure 1 as equations. In order to find integer values of x' and y' that solve the equation 154x' + 69y' = 1, all 1 need to do is substitute 154-2(69) for 16 in equations 2 and 3 and 69-4(154-2(69)) for 5 in equation 3. After collecting terms, I find that 1 = 13(154)-29(69). Thus, x = 13, y — 29 will satisfy the equation 154x' + 69y' = 1. We will call (13,-29) the basic solution to 154x' + 69y' = 1. Is it the only solution? Let us write our equation in the general form again: ax + by = c. Now, let n be any integer and d be the GCD of a and b. If we add to the left-hand side of the equation, we haven't changed it...

(Y, para que no digáis que abuso del tema, me he saltado un artículo que comienza con «Windows can be implemented on almost any system with a memory-mapped display»…)

Me paro en la sección de BIX (ya recordaréis: el extracto en papel que hacía Byte de las conversaciones en su servicio en línea) para contemplar el nacimiento de IFF, el metaformato de archivos presentado por Electronic Arts que debería ser la base de cómo trabajamos hoy, y que permitía encapsular múltiples tipos de información (texto, gráficos y audio, para empezar) en un único archivo.

IFF Graphics Protocol amiga/softw.devlpmt #157, from gregr [Gregg Riker, Electronic Arts] TITLE: IFF (Information Format Files) Is Available! I mentioned that I used IFF files with the SlideShow. Allow me to elaborate. Electronic Arts has a general interest in promoting standards, so we knocked heads with some people at Commodore-Amiga and came up with IFF. IFF is intended to be used by any and all interested developers. It offers a convenient way of allowing programs to exchange data with one another. For example, Graphicraft will be able to exchange files with Deluxe Paint and other EA products. The design is extensible, in that you may add your own types to the standard. There are programs available in C (public domain!) that will read and write graphic images in IFF format. If you're interested in a copy of the spec, please contact Rob Peck at Commodore-Amiga. He can supply you with a copy. If you have any problems or need more information, please contact Jerry Morrison at Electronic Arts, (415) 571-7171. P.S.: IFF covers graphics, audio, and text and is expandable!

Y cierro con una curiosidad. A estas alturas deberíais estar tan enamorados y enamoradas de las ilustraciones de Byte como yo… y esto es tan claro que ya en aquella época la revista vendía ediciones limitadas de sus portadas:

Anuncio de dos ediciones limitadas de reproducciones de portadas de la revista. Una de ellas es una mano robótica dibujando una mano humana junto a una mano humana dibujando una robótica, y la otra es una ilustración de un disquete de cinco pulgadas y cuarto.

Y hasta aquí la Byte del mes. Si queréis hacer los deberes para el mes que viene, como siempre, aquí tenéis los archivos de la revista Byte en archive.org.

Pero, como venimos haciendo últimamente, no nos iremos sin darle un repaso a los episodios del mes de Computer Chronicles…

El primero no es especialmente apasionante, y se dedicaba a las carreras profesionales en informática, incluyendo la emprendeduría… Una cosa a destacar es que no era totalmente necesario tener un grado en informática para encontrar trabajo en el campo: bastaba con unas cuantas asignaturas desde otros grados. Por cierto, que ya hablaban de la importancia de las competencias comunicativas… y ya se comentaba que las mujeres se iban a computer science y no a computer engineering. Tremendo, eso sí, en los breves del final del episodio, cómo AT&T presentaba un sistema de correo electrónico «de bajo coste»: ¡40 céntimos por enviar una página de texto! (Un sello costaba 22). Y con servicio de entrega en mano para personas sin correo electrónico por… ¡siete dólares y medio! ¡De la época! Todo ello mientras IBM presentaba un procesador experimental con 93 000 transistores (el procesador del iPhone 16 tiene… quince mil millones)

En el segundo episodio se hablaba de la computación en paralelo. Solo por ver un superordenador Cray de la época ya vale la pena darle al play. El H. T. Kung al que se entrevista a medio programa, por cierto, está a un grado de separación de Deep Blue, de unos de los primeros «gusanos» de internet, de la fundación de Y Combinator (una de las empresas de capital de riesgo más importantes del Silicon Valley)… y de las TPUs de Google. Se dice pronto. Y el Craig Mundie que sale justo después lideró la investigación y estrategia de Microsoft de 2006 a 2012.

Y para cerrar, dos episodios dedicados a los ordenadores y sus usos militares, otro tema del que seguimos hablando hoy. En esta primera parte se repasa la larga historia de esos usos militares, ya desde el ENIAC, y el enorme papel de DARPA en la investigación en el campo. No os perdáis las demostraciones de simuladores de vuelo de altísima tecnología que palidecen al compararlas con lo que podemos correr hoy en básicamente cualquier PC. Y la investigación en armas autónomas ya había comenzado, con el eventual premio Turing Raj Reddy.

Y en la segunda parte, sistemas informatizados en los barcos de la Armada de los Estados Unidos, capaces de disparar autónomamente (y el rechazo que provocaba la idea entre al menos parte de los militares de la época), o las «star wars» de Reagan… y menciones a coches autónomos.

Os diría que avanzaseis los deberes para anticipar el mes que viene… pero marzo fue el último mes de la temporada 85-86 del programa, y la siguiente temporada no llegaría hasta septiembre.

Y eso es todo por marzo… de 1986. El mes que viene, más.

]]> https://obm.corcoles.net/20260329/byte-marzo-del-86/feed/ 0 10696 Lecturas (2026.I) https://obm.corcoles.net/20260312/lecturas-2026-i/ https://obm.corcoles.net/20260312/lecturas-2026-i/#respond Thu, 12 Mar 2026 13:57:09 +0000 https://obm.corcoles.net/?p=10398 Continuar leyendo "Lecturas (2026.I)"]]> 2025 se quedó en apenas dos entradas de lecturas. A ver si este 2026 nos da más juego (aunque no pinta especialmente bien la cosa). De momento, comenzamos con dos obras leídas íntegramente en 2025 y con una que cerré a uno de enero…

Uno diría que este libro es una novelación de la historia de Ramanujan, probablemente el más famoso matemático del siglo XX, contada por Hardy, uno de los matemáticos más famosos de, al menos, la primera mitad del siglo XX, pero la cosa se va algo más allá. La Wikipedia, de hecho, sitúa al autor, David Leavitt, dentro de la literatura gay. Aunque algo de eso tiene, creo que enmarcar la novela ahí dentro sería limitarla. Sin ser una gran novela, creo que retrata bien a los matemáticos, y de regalo tiene un punto de costumbrismo de la Inglaterra de la época de la Primera Guerra Mundial. Leavitt, por cierto, también es autor de la biografía (esta vez no novelada) Alan Turing. El hombre que sabía demasiado: Alan Turing y la invención de la computadora.

Se agradece mucho, por cierto, que el autor haya tenido la delicadeza de incluir un capítulo de fuentes al final del libro en el que aclara qué es ficción y qué es fruto de sus investigaciones y lecturas.

Javier Rodríguez dibuja (dibujar limita un poco lo que hace este hombre, que es la leche), yo tiendo a comprar, incluso desde que se pasó a DC (uno ha sido siempre muy Marvel, qué le vamos a hacer). Tengo la reedición de Miedo en la pila de pendientes y, una vez metidos en «pijameo»1 puedo recomendar, sobre todo, su maravillosa Spider-Woman (también pasó por la serie Natacha Bustos, otra crac del dibujo; no os perdáis su Moon Girl (y cuando digo «su» quiero decir que es una de las dos creadoras del personaje)) y su History of the Marvel Universe. Pocos creadores hay que tengan su talento para componer visualmente.

Ursula K. Le Guin ganó el Hugo, el Nebula y el Focus con esta novela de 1974, que es una absoluta maravilla. La historia se centra en un físico heredero de Einstein en un futuro muy lejano, y es un ensayo político muy pero que muy interesante. Estremecedora en grado sumo.

Y segundo tebeo de la tanda. De Zerocalcare ya hablamos el año pasado y sigue en su línea con esta obra que, según RTVE, se publicó en Italia en 2017, cuando Zero ya lo petaba por allí, pero en España apenas se había publicado una de sus obras. Zero sigue calcándose (perdón, sé que arderé en el infierno) a sí mismo en su línea pseudoautobiográfica de (para entonces) treintañero de éxito y sus conflictos para compatibilizar ese éxito con sus ideas políticas y con un entorno que no ha tenido tanta suerte en la vida, tirando de puntos de ¿realismo mágico?. Y por aquí no tenemos absolutamente ningún problema con que siga en ello :-).

Y cerramos este primer «lecturas» con Inteligencia artificial: jugar o romper la baraja, de Marga Padilla. El libro, por cierto, está disponible para descarga gratuita (recomiendan donar 3€) siguiendo el enlace. El libro es una muy buena explicación de lo que es la IA, cómo funciona y cuáles son sus potenciales beneficios y riesgos. En este mundo en que nos movemos, una parte del público lo acusará de tecnooptimista, y la otra de tecnopesimista. Servidor piensa que alcanza un equilibrio difícil de encontrar, y que es una muy buena introducción al tema para poder hablar con un mínimo de criterio.

Apa. Dentro de unas semanas (a saber cuántas), más.

  1. Pijameo: dícese de los tebeos de superhéroes, por lo de que los trajes de superhéroes son, de hecho, pijamas. ↩︎
]]> https://obm.corcoles.net/20260312/lecturas-2026-i/feed/ 0 10398 No bloqueo la publicidad: bloqueo tu manera intrusiva de servirme publicidad https://obm.corcoles.net/20260304/no-bloqueo-la-publicidad-bloqueo-tu-manera-intrusiva-de-servirme-publicidad/ https://obm.corcoles.net/20260304/no-bloqueo-la-publicidad-bloqueo-tu-manera-intrusiva-de-servirme-publicidad/#respond Wed, 04 Mar 2026 07:07:46 +0000 https://obm.corcoles.net/?p=10747 Continuar leyendo "No bloqueo la publicidad: bloqueo tu manera intrusiva de servirme publicidad"]]> Me pone de los nervios cada vez que veo el texto de marras. Aquí, la última versión que me he encontrado:

Permite los anuncios para apoyar el periodismo Parece que tienes un navegador, extensión, conexión o antivirus que bloquea la publicidad en nuestro sitio. La publicidad es la única forma de que nuestro trabajo sea posible. Desactiva el bloqueo de anuncios en [nombre del medio censurado]

Apreciado medio: mi navegador no bloquea la publicidad. Es más, entiendo que el uso de publicidad es un modelo como otro cualquiera para financiar un medio de comunicación. No quiero ni pensar la cantidad de publicidad que veo cada día en webs como la tuya. Pero lo que sí bloquea mi navegador son las intrusiones en mi privacidad. Porque no es de ley que no tengas ni el más mínimo interés en buscar alternativas mínimamente respetuosas con mi privacidad para servirme publicidad. Que las hay: insisto en que veo publicidad en la web día sí, día también. A veces, en medios en los que, además, pago una suscripción (este es un tema para otro día).

Añado: sí, me rindo en ocasiones ante este tipo de tácticas, y abro un navegador diferente, en modo privado, y acepto las cookies. Luego las cookies son exterminadas, igual que lo han sido anteriormente, y la publicidad que me sirves es aún menos efectiva que la que estoy dispuesto a ver sin amenazas estériles. Lose-lose, se le llama. Cambia de proveedor de publicidad a algo un pelín más ético. Eso sí sería apoyar el periodismo.

¿Qué uso para proteger mi privacidad? Lo primero es no usar Chrome: no usar el navegador de una empresa que obtiene algo así como el 90% de sus ingresos de la publicidad, quién lo iba a decir, hace maravillas por tu privacidad. Yo uso Firefox, pero con huir de Chrome, aunque sigas usando un navegador basado en Chromium, ya has dado un gran paso (y de entre los Chromiums, mi favorito es Vivaldi). Y, para completar, alguna extensión para controlar los intentos de seguirme más allá de lo razonable. Uno es de Ghostery, pero me dicen que Privacy Badger también funciona muy bien.

Otro texto sobre el tema: No uso nada cuyo propósito es bloquear la publicidad.

]]> https://obm.corcoles.net/20260304/no-bloqueo-la-publicidad-bloqueo-tu-manera-intrusiva-de-servirme-publicidad/feed/ 0 10747 Ventanas partidas en Firefox https://obm.corcoles.net/20260302/ventanas-partidas-en-firefox/ https://obm.corcoles.net/20260302/ventanas-partidas-en-firefox/#respond Mon, 02 Mar 2026 17:09:00 +0000 https://obm.corcoles.net/?p=10735 Continuar leyendo "Ventanas partidas en Firefox"]]> Me entero por este artículo de The Register de que hace ya un tiempo que se puede activar la vista partida en Firefox, que te permite ver dos páginas en una sola ventana del navegador:

Captura de pantalla de un navegador con dos pestañas abiertas en vista partida. A la izquierda vemos un editor de WordPress con esta ventana abierta, a la derecha este blog.

Que me diréis: ¿y no es lo mismo que abrir dos ventanas del navegador? Pues se parece, sí, pero te ahorras unos cuantos píxeles de la interfaz del navegador. Si, como yo, usas pestañas verticales (en mi caso, usando Sidebery), entonces la cosa pasa de ocupar toneladas de interfaz a algo viable:

Captura de pantalla con dos pestañas abiertas en modo partido. A la izquierda vemos la página de The Register mencionada en la entrada, a la derecha este blog. Además, a la izquierda, tenemos un porrón y medio de pestañas mostradas de manera verical ocupando una cantidad importante de píxels.

¿Que cómo se activa?

  • Parece que con Firefox 149 (que debería llegar dentro de tres semanas, el 24 de marzo) la funcionalidad estará disponible por defecto, pero mientras tanto, en Firefox 148 hay que, primero, ir a about:config, aceptar el botoncito que te avisa de que tocar cosas dentro de about:config tiene sus riesgos, buscar browser.tabs.splitView.enabled y activarlo (haciendo doble clic).
  • Y después de activarlo, es tan fácil como «control + clicar» una pestaña y la otra, y después, botón derecho y «Open in split view» (o como se diga en el idioma en que tengas configurado en Firefox)

A partir de ahí, podéis cambiar la cantidad de espacio asignada a cada pestaña arrastrando en la barra que las separa, y desconectarlas haciendo botón derecho en la barra de pestañas y «Separate split view«.

Y este ha sido el bricoconsejo de hoy…

]]> https://obm.corcoles.net/20260302/ventanas-partidas-en-firefox/feed/ 0 10735