Real Alpha

The MAD Podcast · 2 min instead of 1 h 17 m · Oct 8, 2026

LLMs tune databases 85% of the way in 15 minutes

AP

Andy Pavlo

  • Matt TurckHost · Partner, FirstMark

    Publishes the annual MAD landscape of data and AI; sold TripleHop to Oracle.

About this segment

Pavlo says LLMs changed his decade of self-driving database research because they were trained on tuning guides. They get most of the way in minutes, which helps the many teams running default cloud configs.

From “Andy Pavlo: What Happens When Billions of AI Agents Hit Your Database”, Oct 8, 2026. Watch the full episode

“the LLMs can get you maybe 85% of the way there and tuning certain things.”
APAndy Pavloat 34:14 · The MAD Podcast34:14

Takeaways

  1. Earlier ML tuners needed hours of training and scarce production data
  2. LLMs reach about 85% of optimal tuning in roughly 15 minutes
  3. Many users run default cloud configs, so easy wins remain
Watch 2:02 from 33:51

In this episode

Full episode
  1. 10:43Agents could mean 10 to 100x more database queries4:37
  2. 23:38Text-to-SQL reached 99.5% at a bank, but at great cost2:11

  3. 33:51LLMs tune databases 85% of the way in 15 minutes2:02

Up next · Unsupervised LearningPost-training wins inference because the biggest workloads train first2:01