paper
Concrete Problems in AI Safety
paperactive
concrete-problems-in-ai-safety-a41fd7e5·1 events·first seen 28d agoAliases: Concrete Problems in AI Safety
Co-occurring entities
More like this (12)
AI Safety via DebateTowards a Science of AI Agent ReliabilityConfidence-Building Measures for AIVoluntary AI Safety CommitmentsAI Existential RiskDebate (AI safety technique)UK Artificial Intelligence Safety InstituteConcrete MLSafety by Design for Generative AI: Preventing Child Sexual AbuseAI-assisted theorem provingMeta AI (FAIR)AI-driven constraint reasoning
Recent events (1)
Concrete Problems in AI Safety
OpenAI, Google Brain, Berkeley, and Stanford researchers co-authored 'Concrete Problems in AI Safety,' a foundational paper exploring research challenges in ensuring modern ML systems operate as intended. The paper identifies and frames specific technical safety problems for the field. Published in June 2016, it became a landmark reference for AI safety research agendas.