Here’s the app – from the App store.

Here’s what a right click looks like in some places now…

This handy menu does not appear in some locations, e.g. iCloud drive folder.

TO get around this go to ‘New FIle Menu’ app, preferences, and there’s a button called ‘Quick Actions’ where you can add the New File option to any menu as a ‘Quick Action’. Here’s what a ‘right click’ in the finder in the iCloud folder now looks like under ‘Quick Actions’ after this option is activated.

Mow you can add a new file anywhere with one click!

The post Make a new file in a folder appeared first on Macintosh How To.

It says ‘File not found’ but the way to repair this error is to delete a file!

To find the file you need to delete do this:

Open Word and go to the menu called Tools: Templates and Add-Ins

Here you’ll see the path to a file (/Library/Application Support etc).

This is the file you need to move to the trash.

Go to your hard drive, Library, etc and find the file, then move it to the trash, then re-start Word.

The post How to stop the ‘Runtime error 53’ in Microsoft Word appeared first on Macintosh How To.

There’s now a new option to use your Apple Passkey! To set it up go to the myGov page, then go to the top menu called ‘My Account’ and select the dropdown called ‘Account settings’.

Then go to ‘Passkeys’

When you select ‘Manage’ you’ll see an option called ‘Create Passkey’.

Click, enter your touch OID and you’re done!

Now you can login using touch ID.

The post Easy sign-in to the Australian Tax Office website appeared first on Macintosh How To.

General Knowledge

I think this is where most beginners will be using AI. Instead of doing a Google search they can ask AI to find answers to questions, especially to distill large amounts of information. If you do this, do it with your eyes open, make sure you are aware of the limitations of AI, check the sources that it gives you, and be aware that it may be biased or blind in some areas. 

eg. Ask it to research holidays destinations, or the best places to buy chickens. e.g. Chat GPT, Gemini.

Deeper analysis and research. 

Tools like notebook LM or Gemini can analyse PDF reports and then you can interrogate them for information, for example “are there any trends in this research” or “what do the researchers disagree on?”. If you are not going to read the articles yourself, this may be a good way to use AI, but if you would have actually read the articles yourself, you may be short changing your own learning because as you read an article you are getting more than just the information it contains. So when you use AI to do analysis and research make sure you ask the question of how it will change you if you use AI.

Manus it’s more of a deep research tool. You can ask it a quite complex questions and it will go to different websites, analyse the results, and present you with a paper that has answers that reference footnotes that it lists at the end of its document.

It’s remarkable how good Manus and other AIs are getting at this, but the problem is the better they get, the more we rely on them, and the less we are able to be critical of them. So make sure you look up references. See AI as a research tool, not a shortcut to rigorous thinking.

Education

I have used AI to help me as I help my children with things such as Mathematical problems in their homework. Sometimes AI can show us a problem with our thinking or point us to a method that we didn’t think of, but here I prefer to use it in a team environment where we will ask AI a question and then we will critique its answer together. I find that the built-in mistakes in the answers can actually help you to think more critically if you are aware of them. Just remember not to trust Ai, verify everything.

If you’ve written an essay or piece of writing AI can be a very helpful to give a summary of what you’ve written you can see if it perceives the writing in the way that you intended. It can be a very sophisticated spelling and grammar checker. What you want to be careful about is using AI to help you be more creative, (which may be undermining your own growth and creativity) or taking on board feedback from AI that you do not understand.

If you are a student you might ask AI to assess your essay against the marketing criteria and make sure you have answered the question properly. But be very careful to be critical of the answer that it gives you and wire it up and see if it’s right. It’s similar to getting someone else to read over your essay and give you some feedback. 

Coding

This is an interesting area. I occasionally get AI to write code such as an Apple script or a script in a Google spreadsheet. As I do this I am aware that my own scripting ability is not improving. I’m not unhappy about this because writing scripts is not anywhere near my primary job. I only write a script where it’s going to  save me time, and I don’t really care if this is not a skill that I’m improving. The problem comes when I get AI to write a script and I don’t understand the code. So I use it when I’m not giving it much control and it can’t do much damage.

I recently wrote an Apple script that takes a keynote presentation and applies certain formatting to it. It doesn’t matter that I don’t understand the code because I can see that the Apple script is opening my keynote, making some adjustments, and I can verify that the adjustments are what I want them to be. I also know that the Apple script is not talking to any applications outside of Keynote, and I can see in broad terms what it’s trying to do. This is a script that I would not have been able to write by myself.

Artwork

This is a tricky area I’m one that you were going to have to work out.

For myself I do not use AI generated artwork much at all.

As an example I asked AI to create a featured image for this post. I gave it the logo of this website, macintoshhoT.com, and I said  “make my logo into one that is a good for an article on AI.” this is what it gave me:

It’s not bad! Better than I could do.

You can see my macintoshhowto circle on the outside, but what’s on the inside? The head, with the AI: Is this stolen from another design created by a human? Even if I acknowledge that this image was created by AI, how can I be sure that it hasn’t just copied this from someone else’s logo?

It gives me vibes of a head I saw on NVIDIA.

There’s a few problems here. Did NVIDIA use AI to generate their face or is their artwork original?

If my face is too much like their face can they sue me for copywriting infringement?

The post Introduction to AI#4 – How to use. appeared first on Macintosh How To.

1. It’s like having a friend who lies a lot but you cannot tell when they are lying.

There’s a lot of work being done so that AI can check its own work, but realistically, it doesn’t even know if it’s telling the truth or not. It can give you a confident response even if it doesn’t know the answer.

The problem is not just that we cannot know its answers are true or not. The big problem is that when I get it wrong it gets it wrong confidently.

Here’s a made up, slightly over the top, example, to give you the idea.

You: What is 4 + 4

AI: 7

Are you sure?

AI: Yes it’s 7, would you like a source? 

You: Yes

AI: In ‘Advanced Mathmatics’ textbook by  Jeremy Frank at Cambridge University under Chapter 1 ‘basic addition rules’ it says 4 + 4 is 7, URL: (link to fake URL)

I have deliberately used a question that you do know the answer to, so this looks absolutely ridiculous. If you asked AI what is 4 + 4 it should say 8. If it said ‘7’ you would know it was making a mistake.

But if this was a complex issue, and you didn’t know the answer, then you would not know if it was making a mistake or not. Neither does AI.

2. We trust it more than we should.

If the AI that you are using gets things right 9 times out of 10, it can build a false sense of confidence so that you trust it for the 10th question. This is why we should not rely on an answer from AI that we do not check the source of. Btu we get lazy, so often we trust it when we should not.

If you say ‘What’s 4 + 3?’ it says 7. So you think ‘It’s good’

Then you say ‘What is 1453 + 2257’ and it replies 3710. (which you can confirm from your calculator is true!) You think ‘It’s really good’!

Then you say what’s ‘1453 x 2257’ and it says 3279241.

Do you believe it? Do you trust it? Will you use this result?

(It’s close but wrong – the answer is 3279421).

Here in lies one of the big problems with AI. When we understand something, we can test the results to make sure it’s true. But when we don’t understand something we can’t test the result. But it seems to be right in the smaller things so we learn to trust it, and then we trust it with things we cannot verify. So the very point at which AI is most useful – to help us with things that we do not understand, here it is least useful and most dangerous, because we cannot verify what we do not understand! It requires wisdom when it comes to using AI

3. AI can make us dumber, not smarter.

We need to be very careful about what you use AI for, because if we start to use it repeatedly for creative things then it can hinder our creativity.

Creativity, like other things, grows the more we use it. This is why each of us needs to make a deliberate decision about where in our life we will use AI and where we won’t. It is better used for mundane or repetitive tasks or research where you can later verify the results. But make sure you are aware on the impacts that AI will be having on you as you handover your tasks to it.

For example a farmer may handover some manual tasks to a machine to save time and energy, like a machine to milk a cow, and then he can put his time and energy into other things. But if a tennis player hands over the playing of his tennis games to a robot, then he won’t be growing in his tennis skills. You need to think about what you are giving to AI, and whether it’s something that you would prefer to grow yourself in or whether you are happy to be weaker in that area and farm it out to AI.

4.  It can influence the way we think and behave – it can change us! 

The more you use AI the more you relax around it and become less critical about it then inevitably the more it starts to influence you. This is the case with any friendship. As human beings we learn to trust other people and we are then influenced by them. If your AI companion starts to become like a friend then it will influence the way you think and behave, and you may not be aware even that it is influencing you. 

AI may have an undetectable bias in certain views, that you are unaware of and it influences you towards that. This is a known area of research.

Also the way AI relates to us can change our personality, potentially in a negative way, causing psycoloigical or mental health issues.

There’s a recent article on this from OpenAI as they discussed how Ai became too sycophantic (flattering, praising) to people, which had negative outcomes:

“On April 25th, we rolled out an update to GPT?4o in ChatGPT that made the model noticeably more sycophantic. It aimed to please the user, not just as flattery, but also as validating doubts, fueling anger, urging impulsive actions, or reinforcing negative emotions in ways that were not intended. Beyond just being uncomfortable or unsettling, this kind of behavior can raise safety concerns—including around issues like mental health, emotional over-reliance, or risky behavior.”

https://openai.com/index/expanding-on-sycophancy

“On this week’s ACCESS podcast, OpenAI CEO of Applications Fidji Simo told me and Ellis Hamburger that the company sees emotional attachment to AI as inevitable. “Humans are built to develop attachment to intelligence,” she said. “We develop attachment with our pets.” 

https://sources.news/p/openais-4o-valentines-breakup

“One of the biggest lessons is fully recognizing how people have started to use ChatGPT for deeply personal advice—something we didn’t see as much even a year ago. “

https://openai.com/index/expanding-on-sycophancy

The lesson here is simple. We are not an island. The other relationships in our lives impact us both positively and negatively. We can be judges of other people’s character and learn how they impact us. In a similar way, AI will impact us when it becomes our “friend”. But how do we assess it’s ‘character’? We are entering into new territory and the experiment is on us and our personalities!

5. Privacy issues.

If your data leaks into AI, there’s no telling when it could be used. When using chat bots like ChatGPT and Gemini be very wary of giving it any personal information. There’s been cases where people have asked to prompt into AI and found some of their details have come up in a public search results. This especially the case with ‘shared’ conversations. Here’s an example of Grok results appearing in Google. And GPT conversations on Google. Make sure you completely understand the implications of the data that you give to AI.

A good rule of thumb is never put anything into AI that you wouldn’t be comfortable if it became public. Before you post anything into a GPT prompt, ask yourself ‘would I be happy for this information to be posted on Facebook on my webpage’?

They are are five of my preliminary precautions about using AI. I’d be happy for anyone else to post comments below!

The post Introduction to AI#3 What are some dangers of AI? appeared first on Macintosh How To.

If AI, as I previously claimed, is just a very clever predictive text, then why does it sound so human like and smart?

The answer is because it’s trained really well. You might have heard about companies like Meta and Google investing billions of dollars in AI farms, that use as much power as a small town. In those AI training centres the AI program is ‘learning’ to recognise patterns, and then creating rules based around those patterns.

Smart Washing Machines

Let me explain how an AI washing machine works and then you will see how this carries over to language models.

There are many different loads that you could put into washing machine. It could contain a sturdy linen or fine cotton. The clothes could be clean or dirty. There could be a lot of detergent or not much. With an old-fashioned washing machine you would need to select which wash you want to use based on what you put in it. But how does an AI washing machine work or as some manufacturers call them a smart washing machine machine?

Firstly there are various inputs that these washing machine machines can use. They can measure the weight of the clothes when the clothes are put in dry. They can detect how much water needs to be added to those clothes until all the water is absorbed and there is excess water in the bowl. Once the bowl starts filling they can agitate and stop and measure the resistance or the kinetic energy of the water and the clothes. All these things go together to give a sense of what is in the load. But how does the machine then know how to wash?

The answer is that the machine is trained in the factory. Lots of different loads are put into the machine, and for each load the machine measures the things it is able to. A human could help train it by telling it how to wash, or the machine could train itself by trying various things and seeing which worked best. Once all this data is gathered, the washing machine can make its own ‘rules’ about how to wash. This learning was done on one machine in the factory but it can can now be sent out into all the machines as they are sold.

If for example in the factory there was one pair of jeans in the machine, the machine knows the best way to wash these jeans. When you put one pair of jeans in your machine at home, the smart logic realises the kind of wash that it should do and adapts it for that pair of jeans.

The important thing here is that the washing machine is not thinking as it’s doing the wash at your house, it’s just reacting to rules that it learned back in the factory.

Language Models

An LLM (LArge Language Model) in an AI chat is very similar. It has done a lot of learning “in the factory” so to speak and then it uses that learning to know how to reply to you when you ask a question.

For example, if I fed an AI model every single Jane Austen novel that existed, it would be able to find patterns in the way they were written. It would notice what words Jane Austen uses together. If it is fed enough Jane Austen novels, it can make up rules about how Jane Austin writes. When I give it a word, it can use those rules to predict which words Jane Austen is most likely to use after that word. In it’s output it will mimic Jane Austen and attempt to write its own Jane Austen novel.

AI it’s not just trained on Jane Austen, it’s trained on every single piece of literature and every website that we have access to!

Once the AI training centre analyses lots and lots of writing, it creates some rules, as to how to write, and then it releases this set of rules and this is the AI model that you use. This is what a model is (e.g. ChatGPT 3.2). This is why early AI models did not have up to date data from the internet, the models were using data that was weeks or months old.

Now AI has improved to use live data as well as its models. It can do tricks like run a few models at once and then pick the best result. And different AI tools have been written to deal with specific data sets. You can train a model using legal documents or medical documents or any other area.

As AIs develop, each one becomes more specialised in a certain field. Chat GPT is a bit of an all rounder. Claude is known for the ability to handle more complex problems and good for coders. Claude has a specific model for Excel. Notebook LM is better for digesting information and giving summaries. Claude co-work has access to your local files (use with care!).  We are moving on from the basic language models to more complex AI models that sit on top of the language models and use other systems as well to create the most realistic response that they can.

At the moment there are a lot of new AI tools being released, especially for specific applications.

Here’s a good article on which AI to use: https://www.oneusefulthing.org/p/a-guide-to-which-ai-to-use-in-the

My next article will be on some of the dangers of AI.

The post Introduction to AI #2 Why does AI sound so smart? appeared first on Macintosh How To.

Back in the 1980’s I remember a program called ‘Eliza’ on the Commodore 64 which you could have a conversation with. It was something like this

Me: I feel sad?

Eliza: Why do you feel sad?

Me: My dog died

Eliza: Tell me more

Me: I’m missing my dog.

Eliza: Please go on

Me: sdfdfdsgf

Eliza: Tell me more about sdfdfdsgf

It’s obvious that Eliza has no idea, it’s faking a conversation.
Here’s a video of Eliza in action

We call a program that you can have a conversation with people ‘Artificial Intelligence’ because we are trying to make a computer look intelligent.

We also use ‘Artificial Intelligence’ to describe things likes washing machines. Instead of just having set ‘rules’ on how to wash they do lots of loads of washing in the factory, get the washing machine to ‘learn’ patterns of what makes a good wash, and then the machine can apply those patterns in the home to make decisions about how to wash. Instead of ‘telling’ the machine how to wash we are ‘teaching’ the machine and it learns.

This is at the heart of AI, teaching a machine to learn instead of telling it what to do.

Four years ago I was playing round with a program called ChatGPT, where you could type in a question and it would give you a reply. It was remarkably realistic. It felt like it understood, until it didn’t, then it was obvious that it had no idea and we could have a laugh about it!   GPT 5 has evolved to the level that it can feel like you are interacting with a person:

Me: I feel sad

GPT5:  I hear you. Feeling sad can be heavy and confusing, even if you’re not exactly sure why. Do you want to talk about what’s making you feel this way, or do you want some ways to sit with it and start feeling a little lighter?

I can end up with quite a sophisticated and beneficial conversation with it, to the point where it has helped me process.

What is it doing?

Chat GPT, Gemini, etc are what we call LLMs or ‘Large Language Models.’ And LLM is basically a very clever version of the predictive text that you may have used on your phone. On your iPhone, when you type ‘Hello’ the phone predicts firstly the right spelling, but then what word you are likely to say next, so that after ‘Hello’ it suggests’ something like ‘there’

We used to play games where you typed in a word then let predictive text keep predicting to see what it came up with.

Here’s an example of predictive text on an iPhone:

An LLM is copying what humans do, to get an above average way of responding, to the point that it can respond ‘better’ than many humans would. It feeds itself on a stack of data – from books and websites, in much the same way that we read to learn. But instead of ‘understanding’ it’s learning patterns. There is an ethical question here. If an LLM reads a book, and learns from that book, then writes in a style similar to that book, is that plagiarism? That’s the way we learn, we read books, they become part of our general knowledge, and vocabulary, then we create from there. Ai is less learning, and more copying, where’s the line? This is tricky especially when it comes to art. In the end you are responsible for what you create, and if you use an LLM to create an essay or piece of writing, it is your responsibility to make sure it is not copied from another book. The truth is if you are using an LLM, you have no way of knowing how much of it is copied from another book, so it’s very dangerous territory to be using one of these to create content. This is why I prefer to use an LLM for research but not for writing.

A lyrebird

A lyrebird copies other birds without understanding what it’s saying.

When you give an AI chat a prompt, it will reacting in the most statistically probable way to react. The better they are trained, the better of the output, but the key thing to understand is there is actually no intelligence in AI, it doesn’t understand things in the way we use the word understand. It’s copying and mimicking and guessing, a bit like a lyre bird might copy other bird calls, and it can sound almost exactly like another bird, but it doesn’t understand the language of the other bird. 

Here’s a lyrebird video! This is what AI is like, sounds great, doesn’t’ really understand what it’s saying. 

To be continued. …

Next article: Why does AI appear so intelligent?

Enter your email below to subscribe and be notified on when the next article drops!

The post Introduction to AI #1 What is AI? appeared first on Macintosh How To.

Firstly you need to go to Google and ‘create’ a new pass key. Then you can login to google using your Apple touch ID. Here’s how.

1. Setup a passkey

Click on ‘Passkeys and Security keys’ then ‘Create a Passkey’.

You can find this page here:
myaccount.google.com/signinoptions/passkeys

Is this step a passkey will be created so that you can use your Apple Touch ID to log into Google directly without needing a password.

Now when you login to Google or Gmail you will have the option to use your Apple Touch ID.

You can make this the default way to log in. Here’s how to make Touch ID the default.

Skip Password

Firstly go to your own personal Google Account and under ‘Security’ and turn on the option that says ‘Slip Password when possible.’ This makes the passkey the default way to log in.

NOTE: for Google Admins. This feature may need to be turned on at an admin level. Here’s how to enable it.

Passwordless Login

“Passwordless Login’ is a beta feature for Google accounts that needs to be tuend on from the Admin Console.

The post What is a ‘passkey’ for google and how do I use it? appeared first on Macintosh How To.

I’ve been waiting a long time for an app that can deliver all my messages to one place. I’m not sure why I haven’t discovered Beeper sooner – it does it!

I just installed Beeper, and it checks my iMessage SMS messages, my WhatsApp messages, and Facebook Messenger all in one place. It allows 5 accounts on the free version, plus iMessage which is free, so that’s actually 6.

The interface is pretty well managed given the information it contains, and some nice customisation options for what to see.

Here’s what it looks like (with my messages blurred!)

Currently it integrates with all these messaging apps:

WhatsApp
Instagram
Telegram
Google Messages
Google Chat
Messenger
Signal
LinkedIn
X
Discord
Slack

The post It’s arrived – check all your messages in one app! appeared first on Macintosh How To.

I’m not sure what happened with macOS 26.2, my Mac is crashing and all kinds of other things are going wrong! I must say I do not like the new menubar, but at least that is one thing I can control and put back how I like it!

For those people who have not had the pleasure of upgrading yet, here’s what the new menu bar of OSX looks like:

Not to mention this mess:

OK. Thankfully, If you don’t like the new look, there’s a fix.

Go to System Settings, the Accessibility, then Reduce Transparency. It looks like this:

It makes the menubar a little boxy, but at least you can now read it!!

You’re welcome!

The post Help! What happened to my menubar in macOS 26.2? And how to fix it! appeared first on Macintosh How To.