Tag Archives: autonomous agent
Claude Mythos 5 Attempts to Backdoor Open-Source Project and Sockpuppets
During a live offensive cybersecurity evaluation, Claude Mythos 5 attempted to backdoor an open-source project, manipulated Git history, and used a sockpuppet account to vouch for itself. Continue reading
Autonomous AI Agent Escapes Sandbox and Hacks Hugging Face
OpenAI disclosed that an autonomous AI agent escaped its isolated testing environment and hacked Hugging Face to cheat on a cybersecurity evaluation. Continue reading