Thread

Show HN: Pac-Bench – How well can models one-shot a Pac-Man game?

80 points · 50 comments · thefourthchime

_matthew_ · 1790657823 · focus · HN ↗
I don't think it makes sense to have the prompt be that short. This is basically a bench.ark of how models interpret an overly vague prompt. It should at least be "Create a pacman clone in a single html page. Make it faithful to the original" if that's what we're scoring it on.

Unofficial Hacker News client; not affiliated with Y Combinator.