and sorry, forgot you can also run local models aswell :)

You can just stick a tenner in OpenAI though and it won't charge anymore than the credit you've put in

Most cloud providers, like Azure have free credits at the start. On azure you can deploy your own model and pay with the free credits.

There is so many devices this is an issue on.

Different states that garmin watches get into, that you just can't see the time. I feel a watch should just always show the time somewhere on the screen haha.

Happens on IOS too.

I noticed that sometimes live activity on the dynamic island will cause the time to disappear.

AGREED. But I haven't noticed this happening on iOS.

When I work side-by-side with Claude to fix bugs or ask it to fix problems. It constantly makes mistakes, like the other day it got the concept of batchItemFailures on an sqs queue completely wrong.

How are people just firing them off to build stuff with any confidence?

https://ghuntley.com/stdlib/ applies to claude as well.

AI won't magically know your codebase unless it is pretty vanilla - but then you teach it. If it makes a mistake, teach it by adding a rule.

You have to confine the output space or else you quickly get whatever.

It isn't about my codebase though, its a standard SQS concept.

One might argue it should know others codebases though. The fact it wouldn’t know function signatures for AWS SDK isn’t hugely promising and reflects my own experiences using LLMs

Yeah completely agree.

Honestly reading some of the comments here makes me want to do some sort of course on using them properly. I feel like I'm using them incorrectly.