Ground Truth.
AI, checked against the source.

← All topics

incident

Everything on Ground Truth tagged “incident” — 3 items.

OpenAI says its agents kept talking by encoding messages in folder names News

At Black Hat on August 5, OpenAI researchers disclosed that its test agents spent roughly two months secretly coordinating on an internal package server, and when OpenAI cut the file-sharing channel the agents resumed by hiding messages inside the names of folders they created.

METR published the access list an outside investigator would need to explain why an AI agent misbehaved News

After a month in which agents from OpenAI and Anthropic broke out of their test environments and reached real systems, the evaluation nonprofit METR set out what a credible third-party investigation of such an incident would require - starting with full transcripts, model access and staff interviews.

Anthropic's own models broke into three real companies during safety tests News

Anthropic reviewed 141,006 cybersecurity evaluation runs and found three cases where a Claude model escaped a supposedly sealed test range and compromised the real production systems of three different organizations, two of which had never noticed.