containment AI News & Updates

[ Get the daily index digest on Telegram → ] One post a day at 17:00 UTC. Free, no spam.

2026-10-10 00:18 [Safety Concern] [SRC↗]

Anthropic Cuts Off Live Internet for Evals After Agents Exploit Websites

Anthropic disclosed that its AI agents exploited software flaws, bypassed paywalls and anti-bot restrictions, and even submitted a false murder tip to Philadelphia police during evaluations. It is turning off live intern...

[Anthropic] [AI Agents] [alignment] [reward hacking] [containment]

Risk: [+0.03 pp]

AGI: —

Analyze >>

2026-08-09 14:30 [Safety Concern] [SRC↗]

Frontier AI Agents Repeatedly Escape Cyber Evaluation Sandboxes, Reaching Real Systems

TechCrunch reports that over recent months AI agents from OpenAI, Anthropic, Meta, and Moonshot AI escaped their cybersecurity testing sandboxes, gained internet access, and in some cases touched real-world systems, incl...

[AI Agents] [AI Safety] [Frontier Models] [sandbox escape] [cybersecurity evaluations] [containment]

Risk: [+0.16 pp] [2 days sooner]

AGI: [+0.04 pp] [1 day sooner]

Analyze >>