“We audit how we assess understanding of the outputs that were produced... if they can't explain why they built the model that way, that's what we're looking for.”
♫
Said on Unsupervised Learning with Jacob Effron
“You can get a lot from looking at a ton of different rollouts and just trying to understand how the model thinks”
Eric Bigelow · "The Cognitive Revolution" · How Agents Decide: Goodfire's Eric Bigelow on Critical Tokens, Phase Shifts, & In-Context Learning
Play from 26:30
26:30
Audio streams from the publisher’s own feed. Verbatim does not host or copy it.
What was described
Generate many resampled outputs for the same prompt and analyze patterns to understand model decision landscape
Said nearby on the same subject
“I think we've seen a pattern of employees being evaluated on AI usage… tracking usage of tools is the absolute wrong way of going about evaluating output.”
KP
Karine Pagano Talent Rewire
The Mindtools L&D Podcast ·
“The whole edit is a text file… the same command makes the 30 and 60 and the landscape versions from the same take.”
♫
Said on How I AI
“So the first people I hired were basically data scientists. So we really wanted to understand how can we actually try to find insights and patterns out of the data.”
MT
Marcus Tober SEMrush
The SEO Podcast: Page 2 Podcast ·
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.