News for hackers. Stuff that matters.

A comment on GPT-5.5. Parent comment

Re:GPT-5.5 by dakolli on Thursday April 23, 2026 @04:23PM (#47881341)
You know they are 1000% training these models to draw pelicans, this hasn't been a valid benchmark for 6 months +
[ Parent | on HN ]
Re:GPT-5.5 by simonw on Thursday April 23, 2026 @04:41PM (#47881621)
OpenAI must be very bad at training models to draw pelicans (and bicycles) then.
[ Parent | on HN ]
Re:GPT-5.5 by Legend2440 on Thursday April 23, 2026 @04:59PM (#47881874)
Skeptism is out of control these days, any time an LLM does something cool it must have been cheating.
[ Parent | on HN ]
Re:GPT-5.5 by dakolli on Saturday April 25, 2026 @12:46AM (#47898721)
they legitimately suck at everything they don't have concrete examples to copy from.
[ Parent | on HN ]