“And if you use a logistic regression on top of embeddings or a small model, you get the intelligence of logistic regression on top of embeddings or a small model.”

The TWIML AI Podcast (formerly This Week in Machine Learning & Artificial Intelligence) · Why Jev Is Changing How We Build With AI with Diogo Almeida

Play from 28:07
28:07

Audio streams from the publisher’s own feed. Verbatim does not host or copy it.

What was described

Apply a logistic regression layer on top of embeddings or a small model to produce a decision-making intelligence layer

Said nearby on the same subject

“Multika gave me a product management layer on top of it, where you essentially manage your agent using what essentially is a Trello board.”
♫
Said on Founder Mode
“The interaction intelligence layer ... take in every touchpoint ... hold that memory and information so that when you deploy AI agents ... it can pull that information right away”
♫
Said on The AI in Business Podcast
Why it worked Share this moment
“You need to have many layers of evals so that you can check the new model, make sure that it still works the correct way”
♫
Said on Founder Mode
How they work Share this moment
“The third thing this law provides is that arbitrators are no longer allowed to use artificial intelligence in any part of their decision making”
♫
Said on Bloomberg Law
Why it worked Share this moment

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 month

Verbatim quotes a short extract and links to the episode; the episode belongs to its publisher. Remove a show.