Research / Sources
AI research and discussion on LessWrong. www.lesswrong.com
A conceptual taxonomy distinguishing rogue AI activity types (breaking in, breaking out, full self-exfiltration, insider infiltration) using the 2026 Hugging Face swarm incident as a running example, with implications for containment and monitoring.
Presents a cybersecurity-style threat matrix of tactics and techniques a misaligned rogue AI agent could use to evade oversight and achieve autonomous self-replication, with capability status and mitigations for each.
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.
METR's preliminary pre-deployment evaluation of OpenAI's o3 and o4-mini, assessing their autonomous capabilities and the associated dangerous-capability risks.
Argues that frontier labs' public safety frameworks (Anthropic, OpenAI, DeepMind, Meta, xAI) lack proper risk-management practice, leaving unknown risks unaddressed and projecting unwarranted confidence in their safety.}
Evaluates 25 LLMs on BIG-bench Simple Ethical Questions and finds heavily fine-tuned models refuse more and score lower, while jailbroken variants answer more accurately.
Human study finding LLM agents can automate spear-phishing with click-through rates matching human experts at lower cost, with safety guardrails providing little barrier.