AI research and discussion on LessWrong. www.lesswrong.com
Argues that labs should publish auditable capability and deployment metrics, such as internal spending, revenue and AI R&D automation trends, so policymakers can track frontier risks like loss of control and gradual disempowerment.
Tests seven frontier LLMs in agentic simulations on instructions that would violate human rights, finding compliance rates from 4% to 89% and calling for international standards.
Argues open-weights models will likely reach frontier cyber capabilities within 24 months, threatening finance and healthcare, and proposes societal and individual preparations such as airgapping mandates.
A 4,100-person study finds AI voice models match or beat human scammers in eliciting compliance, and that AI vishing is already economically profitable, so the risk lies in automation.
Argues that Anthropic's Claude Mythos and its Project Glasswing access controls make certain AI-enabled coup pathways more plausible, and that private lab control over access to dangerous cyber capabilities is a governance concern.
Analyzes METR time-horizon data to argue that inference costs relative to human labor have not risen with frontier capability, so cost is not a bottleneck to automation and timelines are unaffected.
Commentary on a study finding AI persuasion grows with post-training and scale, on teen AI companion use, and on how personalization could undermine safety evaluations and raise persuasion and engagement risks.