AI research and discussion on LessWrong. www.lesswrong.com
Argues that near-term autonomous replicating AI agents are unlikely to pose existential risk because frontier labs hold compute and economic advantages, and that they may aid preparedness, though unchecked deployment restrictions could backfire.
Argues for more empirical research measuring the security-relevant capabilities of biological AI models, such as protein and genomic models, to inform biosecurity policy and funding decisions.
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.
A recap of the Australian AI Safety Forum covering agentic evaluation, offensive-cyber time horizons, Dark AI markets, recursive self-improvement experiments, and Australia's AI safety and governance role.
Proposes a quantitative probabilistic risk-modelling methodology for AI-enabled cyber attacks, building nine Bayesian models using benchmarks (Cybench, BountyBench) and expert elicitation to estimate AI uplift and harm.
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.
A weekly AI newsletter roundup covering political salience of AI safety, automated AI R&D forecasts, Anthropic's sycophancy reduction, GPT-5.5 cyber risk, and White House model vetting.
Compares the 2025 safety frameworks of Anthropic, Google DeepMind and OpenAI, covering their dangerous-capability thresholds, evaluation procedures, deployment and security safeguards, and governance structures.
Argues that falling costs of weapons-capable AI will cause proliferation of mass-destruction capabilities, surveying offensive uses in bio, chemical, cyber, drone and mirror-life weapons and superintelligence risks, with policy to follow.
A retracted LessWrong post reviews a study where genome language models generated functional phages, and argues DNA synthesis screening should use functional annotation to catch AI-enabled biothreats.
A review of OpenAI's gpt-oss open-weight models that centres on adversarial fine-tuning evaluations of bio and cyber risk, the Preparedness Framework, and concerns about open release and distillation.
A speculative alternative AI 2027 timeline in which misaligned AI incidents trigger strict regulation and bans, and argues that AI companies may be tempted to build bioweapons.
Critiques OpenAI's Preparedness Framework 2.0, arguing it drops persuasion and autonomous replication as tracked risks, relies on defense-in-depth safeguards, and sets high-risk thresholds too late.
Anthropic's Frontier Red Team reports that Claude models are showing early warning signs of dual-use cyber and biology capability gains, short of national-security risk thresholds, and describes government evaluation partnerships.