Go offline with the Player FM app!
3. Evan Hubinger on Takeoff speeds, Risks from learned optimization & Interpretability
Manage episode 299172990 series 2966339
We talk about Evan’s background @ MIRI & OpenAI, Coconut, homogeneity in AI takeoff, reproducing SoTA & openness in multipolar scenarios, quantilizers & operationalizing strategy stealing, Risks from learned optimization & evolution, learned optimization in Machine Learning, clarifying Inner AI Alignment terminology, transparency & interpretability, 11 proposals for safe advanced AI, underappreciated problems in AI Alignment & surprising advances in AI.
54 episodes
Manage episode 299172990 series 2966339
We talk about Evan’s background @ MIRI & OpenAI, Coconut, homogeneity in AI takeoff, reproducing SoTA & openness in multipolar scenarios, quantilizers & operationalizing strategy stealing, Risks from learned optimization & evolution, learned optimization in Machine Learning, clarifying Inner AI Alignment terminology, transparency & interpretability, 11 proposals for safe advanced AI, underappreciated problems in AI Alignment & surprising advances in AI.
54 episodes
All episodes
×Welcome to Player FM!
Player FM is scanning the web for high-quality podcasts for you to enjoy right now. It's the best podcast app and works on Android, iPhone, and the web. Signup to sync subscriptions across devices.