“We build evaluation tools that take expert data sets, expert rubrics, and translate them into a tool that you can actually run to help score what AI is generating”
♫
Said on This Week with EdSurge
“We were able to collect a bunch of experts' rubrics and answers, also supplemented those with synthetic data... graded it against the expert answers with real request RL.”
Unsupervised Learning with Jacob Effron · Ep 94: Applied Compute CEO on the Limits of RL, the New AI Hyperscaler & Why Post-Training Wins Inference
Play from 39:38
39:38
Audio streams from the publisher’s own feed. Verbatim does not host or copy it.
What was described
Collected expert rubrics and answers, supplemented with synthetic data, gave the model access to tools, and graded model outputs against expert answers using real request RL to create a task environment and verifier
Said nearby on the same subject
“You need to interview experts and collect the answers they already gave in multiple forums... for them this finally makes the vacation possible”
♫
Said on The AI Daily Brief: Artificial Intelligence News and Analysis
“The experts used almost an hour of samples to develop a personalized model of the politician's authentic voice.”
♫
Said on TED Tech
“In the Sudan case, experts used a machine learning algorithm trained on over a million examples of synthetic speech to prove, almost without a shadow of a doubt, that it was authentic.”
♫
Said on TED Tech
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.