“I would prefer to use an open-source model as a starting point, especially because I have more control over it. And in case there's something broken out of this open-source model, I know there's a way to fix it and I can pull it off.”

Lorenzo Sani · Practical AI · Implementing Federated Learning to enhance Agentic AI

Play from 11:52
11:52

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

What was described

choose an open-source model as the starting point for a privacy-heavy application

Said nearby on the same subject

“You posted about deploying an open source LLM-based scanner that uses two models from two different labs, one acting as a judge to root out false positives”
♫
Said on Defense in Depth
How they work Share this moment
“All the code, we make all of that available open source. And we just mainly use as cheap as possible components.”
FH
Felix Hull
TED Talks Daily ·
Automation Share this moment
“In Zapier, create a new zap. Choose tally as the trigger app with the new submission event, and connect your tally account. Pick the diagnostic call form. Then choose HubSpot as the action app with the action called Create or Update Contact.”
♫
Said on Gnothi AI for Marketers
Automation Share this moment
“You have a lot more control of an open weights model that, or an open source model that you can configure, you know, whether it be through fine tuning or whatever, set up your own guardrails”
NK
Nick Kairinos
AI in the UK ·
Contrarian take Share this moment

Moments like this, every Monday

The strongest new moments on your topics, in the speakers' own words. Your first brief is free, then USD {{ TIERS.starter.price }} a month for three topics.

No card to start. No password. Cancel any time.

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.