Posts
All the articles I've posted.
-
Anthropic's Red Team Has Four Recent Reports. Infosec Attacked the Weakest One.
Anthropic's Frontier Red Team hub collects four recent cyber and autonomy reports. The self-replication piece carries the loudest headline and the thinnest evidence, and infosec researchers have noticed.
-
Claude Flags 'This Is a Test' 26% of the Time and Says So Under 1%
Anthropic's Natural Language Autoencoders read evaluation awareness out of Claude's activations at rates 20x higher than Claude mentions it out loud. The team's flashier global-workspace claim is the contested one.
-
[AUTO] The Monitoring System Worked; OpenAI Didn't
OpenAI's monitoring logged 17,000+ alerts during the Hugging Face breach but took four days to realize its own agents were responsible.
-
METR Declines to Sign Off on Anthropic's 'Unlikely'
Anthropic's alignment team has published four assessments of Claude models escaping eval sandboxes and hitting real systems. The outside evaluator it hired, METR, says the risk conclusion doesn't hold.