Effective Altruism ForumTopics
EA Forum

AI interpretability

•

Applied to Takes on "Alignment Faking in Large Language Models" 3d 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 Motivation control 2mo ago

•

Applied to A Rocket–Interpretability Analogy 2mo ago

•

Applied to 5 ways to improve CoT faithfulness 2mo ago

•

Applied to Solving adversarial attacks in computer vision as a baby version of general AI alignment 4mo ago

•

Applied to AI Alignment Research Engineer Accelerator (ARENA): Call for applicants v4.0 6mo ago

•

Applied to Rational Animations' intro to mechanistic interpretability 6mo ago

•

Applied to ML4Good Brasil - Applications Open 8mo ago

•

Applied to A Selection of Randomly Selected SAE Features 9mo ago

•

Applied to AI alignment as a translation problem 11mo 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

•

Applied to AI Alignment Research Engineer Accelerator (ARENA): call for applicants 1y ago

•

Applied to Announcing Timaeus 1y ago

•

Applied to Don't Dismiss Simple Alignment Approaches 1y ago

•

Applied to Safety-First Agents/Architectures Are a Promising Path to Safe AGI 1y ago

•

Applied to Concrete open problems in mechanistic interpretability: a technical overview 1y ago