Effective Altruism ForumTopics
EA Forum

AI evaluations and standards

•

Applied to Announcing ForecastBench, a new benchmark for AI and human forecasting abilities 15d ago

•

Applied to Join the $10K AutoHack 2024 Tournament 21d ago

•

Applied to Model evals for dangerous capabilities 23d ago

•

Applied to Submit Your Toughest Questions for Humanity's Last Exam 1mo ago

•

Applied to Thinking About Propensity Evaluations 2mo ago

•

Applied to A Taxonomy Of AI System Evaluations 2mo ago

•

Applied to Case studies on social-welfare-based standards in various industries 4mo ago

•

Applied to [Paper] AI Sandbagging: Language Models can Strategically Underperform on Evaluations 4mo ago

•

Applied to Demonstrate and evaluate risks from AI to society at the AI x Democracy research hackathon 6mo ago

•

Applied to LLM Evaluators Recognize and Favor Their Own Generations 6mo ago

•

Applied to OMMC Announces RIP 6mo ago

•

Applied to Join the AI Evaluation Tasks Bounty Hackathon 7mo ago

•

Applied to Introducing METR's Autonomy Evaluation Resources 7mo ago

•

Applied to How independent is the research coming out of OpenAI's preparedness team? 8mo ago

•

Applied to Biden-Harris Administration Announces First-Ever Consortium Dedicated to AI Safety 8mo ago

•

Applied to Compliance Monitoring as an Impactful Mechanism of AI Safety Policy 8mo ago

•

Applied to The case for more ambitious language model evals 9mo ago

•

Applied to Open-source AI safety projects? 9mo ago

•

Applied to Project ideas: Sentience and rights of digital minds 9mo ago