Anthropic(@AnthropicAI):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.

Anthropic

@AnthropicAI

We're an AI safety and research company that builds reliable, interpretable, and steerable AI systems. Talk to our AI assistant @claudeai on

加入 January 2021

2 正在關注 1.8M 粉絲

Anthropic@AnthropicAI

2025.11.21 19:30

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.