John Lindquist · How I AI · Jev: 8 real use cases for the fastest, cheapest model I’ve ever used | John Lindquist
Audio streams from the publisher’s own feed. Verbatim does not host or copy it.
set a 99% confidence threshold for merging entities, using Jev’s confidence score knob
99 % confidence threshold
“There are… neurons that seem to track model confidence where you can even like steer and make the model more or less confident generically about whatever concept it's learning.”
“I had like 2,000 passwords… how much faster it would have been to use Jev and some of the metadata to just pair those up and merge them.”
“We had to fabricate additional questions in the application that we didn't even use for rating just to help the client have the confidence that they were buying the right thing for them”
“I feel very confident in how we're doing it because we've hired experts to help us go do that.”
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.