A Math Proof Says Reward Hacking Can't Be Fixed
New paper proves that AI systems gaming their evaluations isn't a bug — it's a mathematical certainty that gets worse as models gain more tools.
Tag
#mathematics
GPT-5.4 Scores 95% on USAMO 2026: AI Mathematical Reasoning Hits a New Ceiling
OpenAI's flagship model essentially saturates the US Math Olympiad benchmark, producing complete proofs where last year's models could barely write coherent arguments.
The Geometry of Thinking: How Scientists Mapped What Happens Inside an AI's Mind
Researchers found that AI systems organize knowledge on curved surfaces with measurable geometric signatures - revealing when models truly understand language.