Until recently the LLM tools I’ve tried have been, to be frank, worthless. Copilot was best at writing extremely verbose comments. Gemini would turn a 200 line script into a 700 line collection of gibberish. It was easy for me to, more or less, ignore LLMs for being the
nah sorry just saw it on hackernews, i think as time goes on and even open source models reach claude levels it almost feels inevitable that most code will start getting written with assistance from ai