One interesting feature in this paper is that the programmers who used LLMs thought they were faster, they estimated it was saving about 20% of the time it would have taken without LLMs. I think that’s a clear sign that you shouldn’t trust your gut about how much time LLMs save you, you should definitely try to measure it.

Normally people use ChatGPT to vibe code, this is the first instance I’m aware of of ChatGPT using people to vibe code!

Kris Jenkins is a top-notch interviewer! He lets the interviewee talk, really pays attention and asks good follow up questions. I know that sounds like standard things an interviewer should do but at least in tech podcasts few seem to.