The things people find hard with AI, solved step by step.
We watched what people are stuck on this month, in the forums, the support threads and our own inbox, and wrote the fix for each one. Real products, the exact menu names, and a way to check it worked.
“It makes things up and I can't tell”
How to tell when an AI answer is made up, in under two minutes
The bot sounds the same whether it is right or wrong. That is the whole problem. Here is the check I run before I trust anything that matters.
“It forgets everything I told it”
How to make ChatGPT, Claude and Gemini remember you (and forget what you want)
Every assistant now has two kinds of memory, and the settings moved this year. Ten minutes gets you one that knows your job and your style, and forgets what you tell it to.
“I don't want my chats used for training”
How to stop your chats being used to train AI, on every major assistant
Training on your chats is on by default on all three. Each has one switch to turn it off, each is in a different place, and each leaves something on. Here is all three in ten minutes.
“I don't know which model to pick”
How to pick the right AI model, now that every app has five of them
ChatGPT's picker has five reasoning levels. Claude has Haiku, Sonnet and Opus. Gemini has Flash and Pro. None of the names tell you which to use. The job does.
“It loses the plot in long chats”
How to stop ChatGPT and Claude losing the plot halfway through a long chat
Around the fortieth message the answers get vaguer, it repeats itself, and it forgets the rule you set at the start. Nothing is broken. The chat is full. Here is what to do before and after that point.
“I want AI that runs offline on my laptop”
How to run an AI model on your own laptop, offline, in fifteen minutes
A model that runs on your own machine cannot leak your chats, cannot hit a usage limit and works on a plane. It is also smaller and slower than the cloud ones. Here is how to set one up and when to use it.
“I'm scared to let an agent use my browser”
How to let an AI agent use your browser without handing it your life
An agent that clicks and types in your browser is the most useful and the most dangerous thing in AI right now. I use one daily. These are the rules that keep it from doing damage.
“I keep hitting usage limits”
How to stop hitting the usage limit by Wednesday
You pay for the plan, and on Wednesday it tells you to come back on Saturday. The limit is not a bug. It is a budget, and most people spend it on the wrong things.
Tell us what you're stuck on.
We write these from real questions. Send yours and we'll test the fix and add it here.
hello@sansser.com