| ▲ | holtkam2 3 hours ago | |
at a certain point you're gonna need to change your benchmark because this will end up in the model's training set | ||
| ▲ | simonw 3 hours ago | parent | next [-] | |
Gemini were the team most likely to have this in their training set - see https://x.com/JeffDean/status/2024525132266688757 - and yet their latest model still messes up the bicycle frame! | ||
| ▲ | recursive an hour ago | parent | prev [-] | |
I'm sure that certain point came and went many releases ago. | ||