“The LMs can get you 80, 85% of the way there… people were running with out-of-the-box configuration from Amazon or Google”

The MAD Podcast: How AI Gets Built - with Matt Turck · What Happens When Billions of AI Agents Hit Your Database? (Andy Pavlo)

Play from 35:10
35:10

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

What was described

use an LLM to automatically suggest configuration tweaks for cloud-hosted Postgres/MySQL instances

80-85% improvement

Said nearby on the same subject

“You will write ahead logs in Postgres or binlog in MySQL… replay the changes into a new system when the new schema… essentially zero application code changes.”
SW
Sahil Walia
Software Engineering Radio - the podcast for professional software developers ·
Why it worked Share this moment
“What we tried to do is, you know, using large language models and AI, we tried to really ground probability of success in an empiric data set, where we use Bayesian statistics.”
BB
Brett Bostwick
Business Of Biotech ·
How they work Share this moment
“I assume when you're using Open Router, you can configure it to say I only want ZDR providers.”
PW
Peter Walker
The Startup Podcast ·
How they work Share this moment
“If you can get that information and you can turn that unstructured data into semi-structured data and connect it to the prediction, then you can use the storytelling power of the large language models”
DP
David Porter
Building Tomorrow ·
How they work 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.