kvirani

Also, if they are wrong still, they can rehire. It's not a burn the boats thing.

If it can find flaws in human generated code why not find flaws in self generated code as well?

Does Postman sidestep these weird things about Docker? Or just some of them?

Can AI help here? Asking seriously

Haha thx

Isn't there a case to be made that GenAI makes maintenance of side hussle projects like these easier not harder?

Actual LOL thanks

Something tells me the test suites won't be human written, for most of them. They probably won't be fully human reviewed even.

Sqlite has become the standard? I've been out for a couple years but this is news to me. What does it mean though? Standard for what?

Lore has entered the chat.

I don't get it

It drives me bananas. This post is so triggering.

This resonates as I'm trying to do this more, especially since I'm historically more people-pleasey.

Any resources you suggest?

Muggle question... I don't fully understand what moves the needle further for these frontier models.

Is the training data more valuable ? The training process ? The harness ?

I know they are all important but where are they (all the frontier labs) really pushing to get incremental gains?

Nice. Curious about your views on SolidJS?