OpenAI's merettm says models could be far better at math, they just haven't focused on it

JeffLadish · x · 2026-09-07

Jeff Ladish flags @merettm's claim that they could make their models much better at math but haven't because it isn't a focus. If true, the recent unprecedented math progress is even crazier — it's nowhere near the ceiling.

Related event: OpenAI Reportedly Held Back Its Models' Math Capabilities(2 posts)→

Original post →

More from Models

Models channel →