Training Data · David Silver and Lasse Espeholt of Ineffable Intelligence: A Superlearner for the Age of Experience
Audio streams from the publisher’s own feed. Verbatim does not host or copy it.
built a state-of-the-art reinforcement learning stack that can run at massive scale and ingest data optimally for continuous learning
“We prioritized… a strong pre-training base… then amplified it with reinforcement learning at what we believe to be the largest scale… 10,000 GB-300 for four weeks run documented yet.”
“You implement a minimum viable stack governed by strict data contracts… like enforced UTMs, taxonomy, lifecycle stages. It beats having this massive, drifting tech stack.”
“You have an AI economist ... two level reinforcement learning system ... you can now iterate billions of years of taxation and subsidization and see what is the actual best outcome.”
“I was running the continuous delivery practice for Europe ... optimizing the final mile.”
The strongest new moments on your topics, in the speakers' own words. Free for three topics.
No card. No password. One-click unsubscribe.
Pro watches up to 25 names or phrases and emails you the morning after they are said.
See Pro, $29 a monthVerbatim quotes a short extract and links to the episode; the episode belongs to its publisher. Remove a show.