Anthropic(@AnthropicAI ):A more realistic example: AIs trained to be harmless chatbots can take unsafe actions in agentic settings. Preceding this training with MSM on a realistic spec drastically improves generalization, reducing unsafe agentic actions.

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 https://t.co/FhDI3KQh0n.

Joined January 2021

36 Following 1.2M Followers

Anthropic@AnthropicAI

2026.05.05 20:18

A more realistic example: AIs trained to be harmless chatbots can take unsafe actions in agentic settings. Preceding this training with MSM on a realistic spec drastically improves generalization, reducing unsafe agentic actions. https://t.co/PJcF380iAq