“What if you could provide logit biases to your tool calls to fine-grainy control when things are inserted or not without poisoning your context?”

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 1:20:38
1:20:38

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

What was described

apply logit bias to tool-call logits so the model preferentially selects desired tools and avoids context-heavy native tool calls

Said nearby on the same subject

“We're actually able to bias the model based off of the direct user feedback using some of these like online training methodologies. We're able to see like real upticks in user satisfaction, completion rates, decreased tool call failures”
♫
Said on Unsupervised Learning with Jacob Effron
Automation Share this moment
“…one of our tools called AMI, an assistive tool that we've tested with a variety of hospitals…now involved in a nationwide trial…”
JM
James Manyika Google
Silicon Valley Girl: AI, Tech and Career Growth ·
“A separate copy of the model that’s running on the tool calls to judge whether it’s a safe thing to do… or if it is safe, is it what the user asked for”
AA
Andrew Ambrosino
The Stack Overflow Podcast ·
Automation Share this moment
“The fix is a tool called the Opportunity Evaluator… terms stands for the time, energy, resources, money, and sanity”
♫
Said on The Think Media 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 month

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