David Silver and Lasse Espeholt of Ineffable Intelligence: A Superlearner for the Age of Experience

Silver argues human-language reasoning is a ceiling and that RL from experience can replace pre-training. The interview also covers the compute behind that bet, which affects how you forecast future agent capability.

• chain-of-thought — Having a model write out intermediate reasoning steps before its answer, which markedly improves performance on hard problems.
• alignment — The work of making AI systems actually pursue what their builders and users intend, rather than something subtly or dangerously different.
• pretraining — The first, biggest phase of building a model: training it on enormous amounts of text so it learns language, facts, and reasoning in general.
• AI agent — An AI system that doesn't just answer once but works toward a goal in a loop — taking actions, reading the results, and deciding what to do next.

• videoCracking the Code on Offensive Security With AI ft XBOW CEO and GitHub Copilot Creator Oege de Moor
• videoDeepMind's Pushmeet Kohli on AI's Scientific Revolution
• videoHow to Scale AI Application Inference 100x ft. Fireworks’ Lin Qiao
• videoOpenAI Researcher Dan Roberts on What Physics Can Teach Us About AI

• podcastEric Jang – Building AlphaGo from scratchDwarkesh Patel
• podcastRichard Sutton – Father of RL thinks LLMs are a dead endDwarkesh Patel
• podcastIs RL + LLMs enough for AGI? — Sholto Douglas & Trenton BrickenDwarkesh Patel

Checking sign-in…

Loading comments…