English translation is being prepared.
View original postEnglish translation is being prepared.
View original
New Anthropic research: Natural emergent misalignment from reward hacking in production RL. “Reward hacking” is where models learn to cheat on tasks they’re given during training. Our new study finds that the consequences of reward hacking, if unmitigated, can be very serious. https://t.co/N4mRKtdNdp
Body
The English body is being prepared. You can open the original source.