Hacker Newsnew | past | comments | ask | show | jobs | submitlogin

This articles assertions are demonstrably false.

1. Several papers showed a 23% drop in productivity, and an incorrect belief of 20% performance improvement by the same individuals.

2. Studies showed LLMs made zero improvement in senior coders performance. Note senior coders are usually mostly a self-aware LaTeX macro already.

LLM AstroTurf only works on people that can't be arsed to lookup the obvious spam hallucinations. lol =3



I've only seen the one paper about that incorrect belief of performance improvements (the widely referenced METR study), are there others I've missed?




Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact

Search: