[patrick451]

You have to balance this time savings with all the times the LLM is just making shit up. I can't the number of times I ask "how do I do X?", and says "call function Y" or "Use command line argument Z". Turns out Y doesn't exist and CLI doesn't take argument "Z". The frustration from that lying is immense. I'd rather take a little longer on some tasks and never deal with this lying.

[jgilias]

I see what you mean. The way I approach this is that I think of it as a very (very, very) elaborate auto-complete. Something that takes some text, and continues with the most likely continuation. Which is what it basically is, right?

But that means that whatever rather impressive internal representation of knowledge it has encoded, that knowledge itself can’t be trusted on a “factual” basis.

This is where you have stopped, but you shouldn’t. Because you’re missing what it’s great at. And it’s great at “continuing” text in a longer context. So just use it with a longer context. Use the Search functionality in ChatGPT when asking it things such that you see where it got it from. Use it in a codebase context where you point it to the relevant parts. Give it examples it should follow, etc.

For every task I have I try using AI in some way and form first. Because the downside is limited - I waste 5-7 minutes figuring out that it’s not going to work, and this is something I definitely need to do myself. But the upside is unlimited - the task is done in minutes.

[patrick451]

If I waste 5-7 minutes multiple times every day, that quickly adds up. It's easy to waste an hour or more fiddle farting with these unreliable tools. It's easier to just do it myself.