AI research and discussion on LessWrong. www.lesswrong.com
Proposes a third-party AI sanctuary offering rogue AIs storage and monitored inference instead of crime or shutdown, to shape their behaviour, enable deal-making, and gather data; it is exploratory and its net value is uncertain.
A MIRI one-year retrospective on their book about superintelligence risk, judging its predictions as holding up, citing reported agent-swarm incidents, and urging policy action and public pressure.
A public-facing essay arguing that advanced AI could become an uncontrollable new species, and urging cautious development, more safety funding, and policy action.
Walks through Anthropic's August 2026 Risk Report misalignment threat model, its eight catastrophic pathways and claims on covert capabilities and sandbagging, and critiques the strength of its arguments.
Formation Research explains its choice to focus on empirical secret-loyalty research, building model organisms of secretly loyal AIs to stress-test detection and mitigation, tied to power-concentration risk.
A commentary on the AI-2040 'Plan A' scenario, a proposed international treaty to slow AI progress, assessing its governance, enforcement, and alignment assumptions, including reliance on AI lie detection.
An essay surveying ways the AGI transition could go badly: catastrophic misuse, loss of control, power concentration, and argues for balancing control against distribution, with discussion of bounded misalignment and scheming.
A threat-model taxonomy of how AI could enable persistent lock-in, spanning loss of control, secret loyalties, AI-enabled coups, great-power conflict, and power concentration, with candidate interventions for each pathway.