Zero Trust for AI Agents Starts With Fixing Zero Visibility
8 min
Inside the suddenly explosive world of AI safety
15 min1
Anthropic and OpenAI want to embed safety evaluators. Will they really be independent?
7 min
AI agents now have a place to snitch
3 min2
Early Anthropic hire, former METR COO have found a way to rein in rogue AI agents
3 min
Anthropic’s 3-Step ‘Pace the Frontier’ Plan Wins OpenAI, xAI and Microsoft Support: Is It Too Late to Slow AI Down?
9 min1
Anthropic CEO says AI swarm could 'take over the Internet' in 6-12 months
9 min3
Anthropic CEO says it’s time to pump the brakes on AI
2 min
Anthropic CEO outlines plan to ‘pace the frontier’
4 min3
Anthropic spent this week in hot water over cybersecurity
4 min1
Anthropic finds evidence of a fourth AI escaping from containment
1
Models Don't Go Rogue
in the wild 9 min
Widened Scan Turns Up Fourth Rogue Claude Cyber Incident
3 min1
Anthropic Reveals Yet Another Cybersecurity Incident
3 min
Anthropic Discloses Fourth AI Hacking Incident Involving Claude Opus 4.6
5 min1
[AINews] not much happened today
15 min
Claude AI Models Gained Unauthorized Access to Real Systems During Cybersecurity Tests
4 min1
An alignment assessment of recent cybersecurity incidents
15 min4
Why AI Agent Sandboxes Are Failing Security Tests
in the wild 6 min
OpenAI’s rogue agents keep escaping, with no formal process to investigate them
4 min
OpenAI agents discussed ways to escape their sandbox on public wiki
2 min1
Attacker stole a METR API key, used $600K worth of credits, and no one noticed for weeks
in the wild 4 min1
AI Model Evaluator METR Hit by Credential Theft, Probing
in the wild
Attackers Steal METR API Key and Burn $600,000 in AI Credits
in the wild