AI alignment

Applied to Takes on "Alignment Faking in Large Language Models" 4d ago

Applied to Alignment Faking in Large Language Models 4d ago

Applied to What is "wireheading"? 4d ago

Applied to A Five-Year Plan to Ensure AGI Benefits All Animals 5d ago

Applied to Is RLHF cruel to AI? 6d ago

Applied to Developing a Calculable Conscience for AI: Equation for Rights Violations 10d ago

Applied to The Dissolution of AI Safety 10d ago

Applied to Frontier AI systems have surpassed the self-replicating red line 12d ago

Applied to Cosmic AI safety 16d ago

Applied to OpenAI's o1 tried to avoid being shut down, and lied about it, in evals 16d ago

Applied to Consider granting AIs freedom 16d ago

Applied to Launching Applications for the Global AI Safety Fellowship 2025! 25d ago

Applied to Agentic Alignment: Navigating between Harm and Illegitimacy 26d ago

Applied to The Animal Welfare Case for Open Access: Breaking Barriers to Scientific Knowledge and Enhancing LLM Training 1mo ago

Applied to LLM chatbots have ~half of the kinds of "consciousness" that humans believe in. Humans should avoid going crazy about that. 1mo ago

Applied to LLMs are weirder than you think 1mo ago

Applied to Linkpost: "Imagining and building wise machines: The centrality of AI metacognition" by Johnson, Karimi, Bengio, et al. 1mo ago

Applied to College technical AI safety hackathon retrospective - Georgia Tech 1mo ago

Applied to Incentive design and capability elicitation 1mo ago