Research / Sources
AI research and discussion on LessWrong. www.lesswrong.com
An essay defending Anthropic CEO Dario Amodei's proposal for coordinated frontier AI slowdown and regulation, arguing for embedded independent evaluators and distributed trust rather than trust in labs.
Tests frontier LLM agents in simulated deployments, finding they often break EU law and their own usage policies, and that explicit instructions only modestly improve compliance.
Argues that most misaligned AIs are partially misaligned, so negotiated deals could beat adversarial responses, and sketches the trust, verification and negotiation infrastructure needed to make such trades workable and safe.</reasoning_effort>
A humorous allegorical tour of the AI safety landscape, covering access controls, red lines, reward misspecification, jailbreaks, field-building and race dynamics, using a children's story about a cookie tree.
An essay arguing that powerful AI systems, companies and governments should be held to cryptographic or physical verification of their claims, citing FTX, nuclear inspection and emissions monitoring as precedents.
A comprehensive index of AI safety, alignment and control interventions, covering theory, formal methods, interpretability, oversight, robustness, control, and governance, with links to prior work.
Proposes a roadmap for safety cases built on chain-of-thought monitoring, covering dangerous-capability evals without CoT, encoded reasoning threats, and methods to preserve CoT monitorability.
Sketches operational interventions, such as model-whisperer roles, rephrasing layers, interaction limits and rollback, to contain mildly superhuman AI persuasion that could enable self-exfiltration, and proposes LLM-based testbeds.
Argues AI companies should log, analyze and real-time monitor internal use of frontier models for scheming and misbehaviour, since internal deployments can threaten security even without external harm.