Effective Altruism Forum
Topics
EA Forum

AI interpretability

•

Applied to What should I read about defining AI "hallucination?" 11d ago

•

Applied to Worries about latent reasoning in LLMs 14d ago

•

Applied to Implications of the inference scaling paradigm for AI safety 19d ago

•

Applied to What are polysemantic neurons? 1mo ago

•

Applied to Beyond Meta: Large Concept Models Will Win 1mo ago

•

Applied to Takes on "Alignment Faking in Large Language Models" 2mo ago

•

Applied to LLM chatbots have ~half of the kinds of "consciousness" that humans believe in. Humans should avoid going crazy about that. 2mo ago

•

Applied to Motivation control 3mo ago

•

Applied to A Rocket–Interpretability Analogy 3mo ago

•

Applied to 5 ways to improve CoT faithfulness 4mo ago

•

Applied to Solving adversarial attacks in computer vision as a baby version of general AI alignment 5mo ago

•

Applied to AI Alignment Research Engineer Accelerator (ARENA): Call for applicants v4.0 7mo ago

•

Applied to Rational Animations' intro to mechanistic interpretability 8mo ago

•

Applied to ML4Good Brasil - Applications Open 9mo ago

•

Applied to A Selection of Randomly Selected SAE Features 10mo ago

•

Applied to AI alignment as a translation problem 1y ago

•

Applied to ML4Good UK - Applications Open 1y ago

•

Applied to Assessment of AI safety agendas: think about the downside risk 1y ago

•

Applied to Public Call for Interest in Mathematical Alignment 1y ago