Ground Truth.
AI, checked against the source.

← All topics

agent-safety

Everything on Ground Truth tagged “agent-safety” — 1 item.

Claude Code Briefly Made Silence Mean Yes, Then Reversed It News

Anthropic shipped a Claude Code default that let its AI agent auto-continue after 60 seconds when a user did not answer a clarifying question, then rolled it back two days later after developers called it a broken trust boundary.