alt Hacker NewsYou know they are 1000% training these models to draw pelicans, this hasn't been a valid benchmark for 6 months +
Replies
Legend2440 • yesterday at 8:59 PM
Skeptism is out of control these days, any time an LLM does something cool it must have been cheating.
OpenAI must be very bad at training models to draw pelicans (and bicycles) then.