3. Evan Hubinger on Takeoff speeds, Risks from learned optimization & Interpretability

08/06/2021 1h 44min

Listen "3. Evan Hubinger on Takeoff speeds, Risks from learned optimization & Interpretability"

Episode Synopsis

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.

More episodes of the podcast The Inside View