logoalt Hacker News

scosmanyesterday at 5:33 PM3 repliesview on HN

Community effort happening here to build the ideal dataset: https://github.com/scosman/pelicans_riding_bicycles


Replies

isoprophlexyesterday at 6:42 PM

Wow nice. If an llm could replicate these excellent examples, I'd consider the pelican benchmark fully saturated.

MadameMintyyesterday at 6:28 PM

Nice. Really high quality SVG pelicans riding bicycles here.

phatfishyesterday at 8:25 PM

Come on, don't provide the smoking gun that shows how to draw a pelican riding a bicycle. If it's on the public internet it will end up in training data and invalidate this important LLM capability benchmark.