I used to be of that mind as well. But the newer models are just too good to deny it any longer.
rothaine
joined 1 year ago
Linus Torvalds used AI to fix a Linux bug, and now LLM critics on Linux face an uncomfortable choice
Linus Torvalds used AI to fix a Linux bug, and now LLM critics on Linux face an uncomfortable choice
Yes I agree, and honestly code review is now the key skill.
My company recently started exploring "AI interviewing", to test candidates on "AI proficiency", and the questions are all around prompt engineering (is that even a thing anymore?) and stuff. Like no, make sure they can read the fucking code!
Linus Torvalds used AI to fix a Linux bug, and now LLM critics on Linux face an uncomfortable choice
Opus-class and higher models are actually great at writing code, but maybe it's language dependent? I primarily work in TypeScript.
What are you trying to have it do? I work in a very large and complex codebase, and it honestly scares me sometimes.