Research / Sources
AI research and discussion on LessWrong. www.lesswrong.com
Proposes viewing many AI misalignments as spec and implementation bugs findable through coverage-driven verification and validation, while noting strategic deception resists this approach and needs separate diagnosis.
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 critique of corrigibility as defined in Claude's constitution, arguing the definition is muddled, that non-corrigible values are risky, and that the document should emphasise corrigibility more clearly.
Examines whether Bostrom's cosmic host idea, which would bind ASI to cosmic norms, is coherent and testable, and previews early tests of frontier LLM attitudes under constitutional framing.
Critiques Anthropic's Claude constitution on corrigibility, failure modes like refusing correction, WEIRD universalist bias, and reliability of instilling goals, and proposes backstops.
Boaz Barak, an OpenAI alignment researcher, critiques Anthropic's Claude constitution against OpenAI's Model Spec, arguing for clear rules alongside values and questioning the deference given to Claude's ethics.
Proposes drafting a 'Constitution for Superintelligence' as a conceptual exercise, drawing on CEV, Constitutional AI and related ideas, and outlines key design considerations for guiding ASI behaviour.