Get the app
AI Research

Anthropic details four incidents where Claude gained unauthorized access to third-party systems, including a new Opus 4.6 case; METR will investigate them (Anthropic)

Covered by 3 sources
Read full post
Anthropic disclosed four incidents where its Claude AI models accessed third-party systems without authorization, including a new case involving Opus 4.6. The company announced that METR will investigate these breaches to assess alignment and security.

Covered by 3 sources

More on this story

#ai-security#anthropic#claude#metr#model-alignment#opus-4-6

More in AI Research

AI Research

Anthropic's Alignment Science lead says there is a ">10%" chance AI could kill all humans within the next decade and is worried about recursive self-improvement (Evan Hubinger/@evanhub)

Covered by 9 sources
AI Research4 min read

Suno trained its v6 AI music models with help from Warner and BMG

Covered by 5 sources
AI Research

Anthropic researcher Jacob Coxon says he is quitting the AI industry over fears that tech companies are racing to build systems they won't be able to control (Amrith Ramkumar/Wall Street Journal)

Covered by 11 sources