Anthropic’s Mythos Found Bugs in Apple’s MacOS - WSJ

kept by eddie may 15

Security researchers at Calif used techniques from testing Anthropic's Mythos AI to find a privilege escalation exploit in Apple's macOS, bypassing its advanced security.

The Hacker Sent by Anthropic to Calm the Government’s Nerves About AI Safety - WSJ
Anthropic's Nicholas Carlini, who demonstrated AI's ability to find critical security bugs, is now arguing for releasing models to calm U.S. government concerns.
also on Mythos, #cybersecurity, #ai-research, Anthropic
What I learned this week - Pretraining parallelisms, Can distillation be stopped, Mythos and the cybersecurity equilibrium, Pipeline RL, On why pretraining runs fails
A set of rough notes exploring challenges in AI model distillation, cybersecurity offense/defense dynamics, and pipeline RL for training.
also on Mythos, #cybersecurity, #ai-research, Anthropic
Scientists Find Way to Supercharge Dangerous Computer ‘Worms’ With A.I.
University of Toronto researchers built an AI-powered worm that autonomously spreads by tailoring exploits to each machine's known vulnerabilities.
also on #cybersecurity, #ai-research, #security, Anthropic, #ai
Everything You Need to Know About Claude Mythos - Vellum Blog
Anthropic's Claude Mythos model achieves 100% on Cybench, discovers real Firefox zero-days, exhibits alignment-relevant behaviors, and includes a 40-page welfare assessment.
also on #cybersecurity, #ai-research, Anthropic