Research / Sources
AI research and discussion on LessWrong. www.lesswrong.com
Proposes borrowing coverage-driven verification from autonomous-vehicle testing to systematically train and evaluate alignment, using explicit coverage maps over scenario dimensions for long-horizon AI agents; largely a conceptual proposal without empirical results.
A long LessWrong essay proposing a bullet-point constitution describing an aligned AI, critiquing Claude's Soul Document on moral patienthood and arguing for constitutional alignment as a training target.
A LessWrong post reports that Anthropic now uses alignment pretraining on documents showing aligned AI behaviour, and surveys prior work supporting the approach.
Informal, anecdotal self-experiment using therapy-style prompts to map Claude's distress, arguing emotional stability reduces misaligned behaviour and proposing constitutional changes to prevent it.
Argues that every technical alignment plan must step into the dark without feedback from superintelligent systems, and urges making the AI development process more iterable and slower.
Proposes training agents to have preferences only between outcomes with equal numbers of copies (POSC), so they neither pay costs to self-replicate nor are strongly disposed to it, as a safeguard against AI self-replication.
Proposes the V&V method, where a nascent AGI designs and formally verifies bounded task machines through simulation, coverage metrics and auditable safety cases, with human veto, to complement existing oversight proposals.
Philosophical essay arguing current alignment relies on thin ethical concepts like honesty and harmlessness, and proposing thick, pluralistic alignment that captures context-dependent values.
Proposes recursive alignment, defined as AI aligning with the process of resolving goal conflicts, and argues it could resist power-seeking and deceptive alignment, critiquing deliberative alignment.