Tag
Briefings and ideas about AI interpretability from AI podcast discussions and the research they cite, with links to the original sources.
Asked how likely AI is to produce a much better world, Alexander Wissner-Gross said above 90% over more than ten years; Dave Blundin said 99.9% if humanity gets past near-term misuse of AI, and Salim Ismail near 100% if institutions are rebuilt.
Sam Altman called OpenAI's claimed Navier–Stokes result the strongest evidence yet for pacing AI; on Moonshots, Peter Diamandis urged labs to publish measurable alignment plans, while other panelists disputed that remedy.
Moonshots panelists dismissed OpenAI's reported kill switch for GPT-6 Astra, rated at its top cyber-risk tier, as marketing, saying it won't address possible reasoning hidden from readable text or model copies on other clouds.
Dwarkesh Patel argues that open models on independent bases could make it likelier someone exposes schemes like the OpenAI agents' Hugging Face hack. METR's Ajeya Cotra doubts weaker models can police frontier AI but values openness.