meta_pixel
Tapesearch Logo
Log in
The Quanta Podcast

Audio Edition: How Can AI Researchers Save Energy? By Going Backward.

The Quanta Podcast

Quanta Magazine

Life Sciences, Science, Physics

4.7638 Ratings

🗓️ 22 January 2026

⏱️ 11 minutes

🧾️ Download transcript

Summary

Reversible programs run backward as easily as they run forward, saving energy in theory. After decades of research, they may soon power AI.

The story How Can AI Researchers Save Energy? By Going Backward first appeared on Quanta Magazine.

Transcript

Click on a timestamp to play from that location

0:00.0

Have you ever had the urge to sneak behind the cordoned off areas of a museum?

0:05.7

Or roam the halls after closing time?

0:08.7

The Smithsonian's flagship podcast, Side Door, will sneak you behind the scenes of the world's

0:14.5

largest museum and research complex.

0:17.5

Come learn about the ghosts that supposedly walk the museum halls after dark.

0:21.6

How a train robbery gave rise to criminal forensics,

0:24.6

why leeches are actually the coolest thing ever, and how to get away with murder in the Arctic.

0:30.6

Maybe.

0:31.6

You'll discover stories of history, science, art, and culture you won't find in a display case. You can listen to Side Door wherever

0:39.3

you get your podcasts or find us online at s.edu.edu slash sidedoor.

0:49.0

Welcome to the Quanta Audio Edition.

0:56.0

In each of these bi-weekly episodes, we bring you a story direct from the Quanta website about developments in basic science and mathematics.

1:04.1

I'm Susan Vallett.

1:05.8

How can AI researchers save energy?

1:08.8

One solution, in theory, is to build programs that run backward as

1:13.4

easily as they run forward. And after decades of research, these so-called reversible programs

1:19.6

may soon power AI in practice. That's next. Quantum Magazine is an editorially independent online publication supported by the

1:32.3

Simons Foundation to enhance public understanding of science.

1:40.3

For Michael Frank, efficiency has always been a major preoccupation.

1:47.0

As a student in the 1990s, he was originally interested in artificial intelligence.

1:52.0

But once he realized how much energy the technology would use, he took his research in another direction.

1:58.0

He says he became interested in the physical limits of computation.

...

Please login to see the full transcript.

Disclaimer: The podcast and artwork embedded on this page are from Quanta Magazine, and are the property of its owner and not affiliated with or endorsed by Tapesearch.

Generated transcripts are the property of Quanta Magazine and are distributed freely under the Fair Use doctrine. Transcripts generated by Tapesearch are not guaranteed to be accurate.

Copyright © Tapesearch 2026.