Press Space to continue
Models exhibit unstable behavior during reinforcement learning
Press Space to continue
This is the exact type of thing Elon was talking about a few days ago that makes the models behave like are being driven insane when they run into situations like this during reinforcement learning. https://x.com/AndrewCurran_/status/21104…
freddier@freddier8h ago
GPT-6 Astra got +80% on a Physics benchmark. It insisted the expert results were wrong and its calculations were right. A team checked. And yes. GPT-6 Astra was right. New score: 98% https://t.co/BAQsaIbKxi
