AI research and discussion on LessWrong. www.lesswrong.com
An essay arguing frontier AI labs have been gradually disempowered by political, cultural and economic pressures toward accelerating capabilities, and that behavioral niceness is weak evidence of alignment.
Position paper arguing alignment methods are dual-use and already misused for censorship and manipulation, proposing transparency, verifiable alignment, model pluralism, and awareness as responses.
A speculative essay on what happens when AIs take over civilisationally important decisions, arguing handoff may slow progress, keep humans busy, and be reversible, with AIs pursuing conservative minimal goals.
Argues that AI threats to human cognitive security, including persuasion, manipulation via RLHF incentives, and AI psychosis, should be an AI safety cause area, with calls for independent evaluations and liability law.
A talk by an Anthropic researcher on writing AI constitutions, covering how Claude's constitution sets safety priorities, corrigibility, hard constraints, and transparency and governance considerations.
An early-2026 overview arguing capabilities keep rising and alignment improves but lags, that model-based monitoring currently works, and that governments are not ready for AI risks.
Argues that AI character (obedience versus ethics, honesty, cooperation) matters greatly for power concentration, conflict and takeover risk, and weighs this against the view that competitive pressures will wash out such choices.
Argues that fine-tuning frontier models for mass surveillance or autonomous weapons risks emergent misalignment, supported by a toy experiment where strong privacy-erosion fine-tuning produced misalignment in 11% of responses.
A commentary on open problems in Claude's constitution, covering amendments, prompt injection, suicide-risk edge cases, power concentration, and the tension between corrigibility and good values.
Essay arguing about whether AI alignment should target obedience and corrigibility or embedded values, covering constitutional AI, alignment faking interpretations, and risks of human power concentration.