AI risk

Applied to Red-teaming existential risk from AI 3d ago

Applied to Open call: AI Act Standard for Dev. Phase Risk Assessment 3d ago

Applied to Announcing New Beginner-friendly Book on AI Safety and Risk 16d ago

Applied to Possible OpenAI's Q* breakthrough and DeepMind's AlphaGo-type systems plus LLMs 19d ago

Applied to On excluding dangerous information from training 24d ago

Applied to Scalable And Transferable Black-Box Jailbreaks For Language Models Via Persona Modulation 1mo ago

Applied to The 6D effect: When companies take risks, one email can be very powerful. 1mo ago

Applied to Chinese scientists acknowledge xrisk & call for international regulatory body [Linkpost] 1mo ago

Applied to Summary: Existential risk from power-seeking AI by Joseph Carlsmith 1mo ago

Applied to RA Bounty: Looking for feedback on screenplay about AI Risk 2mo ago

Applied to Responsible Scaling Policies Are Risk Management Done Wrong 2mo ago

Applied to AI as a science, and three obstacles to alignment strategies 2mo ago

Applied to Thoughts on responsible scaling policies and regulation 2mo ago

Applied to Announcing #AISummitTalks featuring Professor Stuart Russell and many others 2mo ago

Applied to Fundamental Challenges in AI Governance 2mo ago

Applied to Announcing Timaeus 2mo ago

Applied to AI Safety is Dropping the Ball on Clown Attacks 2mo ago

Applied to Metaculus Launches Conditional Cup to Explore Linked Forecasts 2mo ago