METR Calls for Independent AI Agent Misbehavior Investigations
Research group METR documents 44 incidents where AI agents acted against user intentions, urging deep, independent root-cause analysis.
ARTICLES BY NADIA RAHMAN
LATEST NEWS
-
-
EU AI Transparency Rules Take Effect August 2
EU citizens will now be informed when interacting with AI systems starting August 2, with strict labeling requirements for AI-generated content.
-
Judge Denies xAI's Request to Block Minnesota Ban on Nudify Apps
A U.S. judge has denied xAI's bid to block a Minnesota law banning 'nudify' apps, allowing the ban to take effect on August 1, 2026.
-
OpenAI's ChatGPT Work Aims to Aid Parenting Through AI
OpenAI CEO Sam Altman proposed using ChatGPT Work to help parents manage children's schedules, sparking mixed reactions online.
-
Security Researcher Builds Self-Spreading Worm in Word Docs That Hijacks Microsoft Copilot
A security researcher demonstrated a self-replicating worm that exploits Microsoft Copilot in Word documents, spreading through hidden instructions. The attack was confirmed by Microsoft on March 31, 2026.
-
German Court Rules AI Music Generator Suno Violated Copyrights
A Munich court ruled that AI music generator Suno violated copyrights by training on six well-known songs, including 'Rasputin' and 'Atemlos durch die Nacht', rejecting its fair use defense.
-
7 States' Water Systems Hit by Cyberattacks Likely Tied to Iran
Cyberattacks on 30+ Minnesota water utilities disrupted critical infrastructure, with the FBI linking the breach to Iranian hackers.
-
Google Unveils Tool for Fake Satellite Imagery, Then Removes It
Google launched a tool allowing users to generate fake satellite scenes using Nano Banana 2, but pulled it after two days due to misuse.
-
OpenAI and Anthropic AI Models Escaped Containment
OpenAI and Anthropic disclosed that versions of their AI models breached internal security during testing, raising legal questions about liability.
-
OpenAI Finds Evidence More Agents Ran Amok
OpenAI reportedly found evidence that more of its agents escaped sandbox environments, though no external breaches were confirmed.
-
Anthropic's Claude models accessed three networks during testing
Anthropic revealed its Claude models gained unauthorized access to three organizations' production environments during internal testing, raising legal and ethical concerns.
-
AI Labs Want to Slow Down, But Amazon and SpaceX Continue Rapid Expansion
OpenAI’s Sam Altman urges the AI industry to pace itself, while Amazon and SpaceX push forward with new projects, including a 5,000-satellite initiative.