Eye On A.I. cover image

#130 Mathew Lodge: The Future of Large Language Models in AI

Eye On A.I.

00:00

How DiffBlue's Product Can Find Better Code

DiffBlue's product does the same thing, we search for unit tests. So essentially what they did is use reinforcement learning to try different moves. They say tried different implementations of the quicksort algorithm and this is down at the assembly language level. For quicksort the implementations are about 1.7% faster for a large array of numbers which doesn't sound like much until you remember that this is a function that you get called millions of times.

Transcript
Play full episode

The AI-powered Podcast Player

Save insights by tapping your headphones, chat with episodes, discover the best highlights - and more!
App store bannerPlay store banner
Get the app