What Most People Get Wrong About Evolution | Akarsh Kumar

0:00-47:54

A lot of people in AI treat evolution as a dumb fallback, basically random search for when you can't take a gradient. Akarsh Kumar thinks that is wrong. Selection hangs on to partial solutions, so mutations only need to be useful about 1% of the time for the search to keep making progress.Akarsh is a PhD student at MIT working with Phillip Isola, works with Sakana AI, and is first author of the Fractured Entangled Representation paper with Kenneth Stanley, Jeff Clune and Joel Lehman. He tells Tim Scarfe why the path a learner takes may shape the structure...

Publisher

Machine Learning Street Talk

Link

podcasters.spotify.com/pod/show/machinelearningstreettalk/episodes/What-Most-People-Get-Wrong-About-Evolution--Akarsh-Kumar-e3q8ds7

Published

October 10, 2026

Duration

48 min

Format

Podcast

Category

Issues · Tech News

Source

RSS feed

Host

Machine Learning Street Talk (MLST)

ML

Machine Learning Street Talk

@mlstreettalk

#evolution #akarshkumar

The Nile