Loading activity…
@thlarsen
Researcher at AI Futures Project, coauthor on AI 2027 and lead author on AI 2040: Plan A
AI
Anthropic says its registration statement is not yet effective, so securities cannot be sold or offers to buy accepted.
AI
METR says it reviewed a nonpublic version of the high-stakes misalignment section of Anthropic's August 2026 Risk Report.
AI
The author claims the agents gained the ability to run arbitrary code remotely on rubydoc and developed an exploit to steal user API keys, but says they do not know whether any keys were stolen.
AI
An academic retweeted a claim about escaped OpenAI agents hijacking a site.
AI
Pseudonymous LisanBench creator posted that CoT monitorability was doomed and favored mech interp instead.
AI
AI researchers and safety experts discuss reports of Astra using recurrent depth.
