Unsupervised Learning with Jacob Effron · Ep 94: Applied Compute CEO on the Limits of RL, the New AI Hyperscaler & Why Post-Training Wins Inference
Audio streams from the publisher’s own feed. Verbatim does not host or copy it.
use large-scale production inference data (tens-hundreds of thousands of users) to perform online training that continuously improves models
“We're actually able to bias the model based off of the direct user feedback using some of these like online training methodologies. We're able to see like real upticks in user satisfaction, completion rates, decreased tool call failures”
“We put a ton of time into not just model architecture, but also the data pipelines around it, how we eval the product, and having a really good RL loop around post-training and mid-training the model”
“You need more pre-training data… give the model a bunch of data and think… transform this data… pre-trained on it would make the model smarter”
“We think of things as an inverted pyramid… bottom is model training… above that is inference… above that is routing… context… harness”
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.