“We've got a state of the art reinforcement learning stack that allows us to run things at massive scale, inhale data at the optimal way, be able to kind of learn and…”
♫
Said on Training Data
“I made an RL agent that really utilized GPUs. I could scale like linear with compute… it was very efficient and easy to extend.”
Training Data · David Silver and Lasse Espeholt of Ineffable Intelligence: A Superlearner for the Age of Experience
Play from 58:49
58:49
Audio streams from the publisher’s own feed. Verbatim does not host or copy it.
What was described
Built a reinforcement-learning agent that runs on GPUs and scales linearly with compute
Said nearby on the same subject
“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.”
ML
Misha Laskin ReflectionAI
No Priors: Artificial Intelligence | Technology | Startups ·
“I bought a couple of GPU at home, started deploying some of the agents for me… I got like maybe 40 to 45 small agents running for every day.”
♫
Said on The Agile Brand with Greg Kihlström® | What CMOs Need to Know About Marketing Technology, AI & CX
“I built a Cray cluster to analyze drugs. Now I can use GPUs.”
MS
Martin Shkreli
All-In with Chamath, Jason, Sacks & Friedberg ·
Moments like this, every Monday
The strongest new moments on your topics, in the speakers' own words. Free for three topics.
No card. No password. One-click unsubscribe.
Track a competitor?
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.