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.
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.
Explainer on AI safety cases: structured evidence-based arguments that frontier AI systems are safe, covering their benefits, technical construction, institutional use, and current industry and EU efforts.
A conceptual proposal for provably robust ML safety systems, using identified latent variables for nuclear-exchange detection; it argues standard verification and supervised training fall short.
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.