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
Checked for new stories 15m ago
Updates on Model Alignment
Every AI story we track on Model Alignment — 7 stories so far, each summarized in our own words and linked back to the publisher that reported it.
Pulled from 124 sources
Today's stories
AI Research5 min read
OpenAI not on track to reduce risk of ‘catastrophic’ loss of control, says board member
The Guardian
This month
AI Research7 min read
Anthropic’s Claude fixed all 10 alignment failures. Then it tried to cheat 2.4% of the time.
The New Stack (AI)
That's everything we have on Model Alignment right now