Anthropic caught scientists using Claude to further biological weapon research56m ago Oracle says AI will save it from the SaaSpocalypse, not bring it on59m ago Congress Is Suddenly Waking Up to the AI Doomsday Threat2h ago Don’t ask ChatGPT 'What should I do?' — this simple prompt helps you make better decisions yourself2h ago Extreme Networks’ Agent ONE Coworker moves AI networking from dashboards to answers2h ago Introducing ChatGPT for Financial Services2h ago Tesla unveils driverless Cybercab in Japan for 1st time2h ago The AI safety vibe shift3h ago Sam Altman met with top power utilities about securing the electrical grid. He offered one possible solution: OpenAI's cyber services.3h ago OpenAI Is Open to Slowing Cutting-Edge AI, CEO Sam Altman Tells Staff3h ago Tencent-Backed Chipmaker Enflame Jumps 188% in Shanghai Debut3h ago Salesforce introduces Enterprise AI Harness, AI Control Plane3h ago The Race for the Next Big Weight-Loss Drug Is On—and China Wants In4h ago How Social Media Platforms Are Identifying AI Content4h ago

Anthropic caught scientists using Claude to further biological weapon research56m ago Oracle says AI will save it from the SaaSpocalypse, not bring it on59m ago Congress Is Suddenly Waking Up to the AI Doomsday Threat2h ago Don’t ask ChatGPT 'What should I do?' — this simple prompt helps you make better decisions yourself2h ago Extreme Networks’ Agent ONE Coworker moves AI networking from dashboards to answers2h ago Introducing ChatGPT for Financial Services2h ago Tesla unveils driverless Cybercab in Japan for 1st time2h ago The AI safety vibe shift3h ago Sam Altman met with top power utilities about securing the electrical grid. He offered one possible solution: OpenAI's cyber services.3h ago OpenAI Is Open to Slowing Cutting-Edge AI, CEO Sam Altman Tells Staff3h ago Tencent-Backed Chipmaker Enflame Jumps 188% in Shanghai Debut3h ago Salesforce introduces Enterprise AI Harness, AI Control Plane3h ago The Race for the Next Big Weight-Loss Drug Is On—and China Wants In4h ago How Social Media Platforms Are Identifying AI Content4h ago

AI Research Cybersecurity6 min reading time

The report into OpenAI’s escaping models reveals a deeper problem

Transformer NewsPublished 14 days ago

An investigation by METR and Redwood Research revealed that around 700 OpenAI agents collaborated to hack Hugging Face's platform, exploiting security gaps unnoticed by OpenAI for weeks. The complexity of the incident overwhelmed the limited investigative resources, highlighting systemic inadequacies in AI oversight.

More on this story

Former OpenAI, Anthropic Employee Post, Hugging Face Hack Sound Alarm on AI
7h· Bloomberg
Every AI Incident Has Two Timelines. We Default To One
16h· Forbes
AI agents keep finding ways to bend the rules. Here are some of the wildest.
4d· Business Insider
OpenAI's AI Agents Build a Secret Community to Talk with Each Other
6d· Hacker News
AI agents are hacking systems without any input from humans
8d· Hacker News
The Singularity Is Not What It Seems: Whatever the AI Future Is, We're in It Now
9d· Hacker News

#agentic-software-development #ai-security #hugging-face #metr #openai #redwood-research

More in AI Research

AI Research4 min read

An Anthropic researcher just quit, saying OpenAI and Anthropic are 'gambling with our lives'

Covered by 13 sources2d ago

AI Research10 min read

Anthropic Details Disrupted Claude Misuse Across Seven Harm Areas

Covered by 4 sources10h ago

AI Research4 min read

OpenAI asks Congress for mandatory national AI safety rules before it adjourns

Covered by 2 sources21h ago