meta_pixel
Tapesearch Logo
Log in
Into the Impossible With Brian Keating

The Mysterious Math Behind LLMs - Anil Ananthaswamy - #537

Into the Impossible With Brian Keating

Brian Keating

Physics, Natural Sciences, Science

4.71.1K Ratings

🗓️ 23 January 2026

⏱️ 69 minutes

🧾️ Download transcript

Summary

WANTED: Developers and STEM experts! Get paid to create benchmarks and improve AI models. Sign up for Alignerr using our link: https://alignerr.com/?referral-source=briankeating One of the most powerful AI systems we’ve ever built is succeeding for reasons we still don’t understand. And worse, they may succeed for reasons that might lock us into the wrong future for humanity. Today’s guest is Anil Ananthaswamy, an award-winning science writer and one of the clearest thinkers on the mathematical foundations of machine learning. In this conversation, we’re not just talking about new demos, incremental improvements, or updates on new models being released. We’re asking even harder questions: Why does the mathematics of machine learning work at all? How do these models succeed when they suffer from problems like overparameterization and lack of training data? And are large language models revealing deep structure, or are they just producing very convincing illusions and causing us to face an increasingly AI-slop-driven future? KEY TAKEAWAYS 00:00 — Book explores why ML works through math 02:47 — Perceptron proof shows simple math guarantees learning 05:11 — Early AI failed due to single-layer limits 07:12 — Nonlinear limits caused the first AI winter 09:04 — Backpropagation revived neural networks 10:59 — GPUs + big data enabled deep learning 15:25 — AI success risks technological lock-in 17:30 — LLMs lack human-like learning and embodiment 22:57 — High-dimensional spaces power ML behavior 27:36 — Data saturation may slow future gains 31:11 — Continual learning is still missing in AI 33:46 — Neuromorphic chips promise energy efficiency 41:49 — Overparameterized models still generalize well 45:05 — SGD succeeds via randomness in complex landscapes 48:27 — Perceptrons remain the core of modern neural net - Additional resources: Anil's NEW Book "Why Machines Learn: The Elegant Math Behind Modern AI": https://www.amazon.com/Why-Machines-Learn-Elegant-Behind/dp/0593185749 Get My NEW Book: Focus Like a Nobel Prize Winner: https://www.amazon.com/dp/B0FN8DH6SX?ref_=pe_93986420_775043100 Please join my mailing list here 👉 https://briankeating.com/yt to win a meteorite 💥 - Join this channel to get access to perks like monthly Office Hours: https://www.youtube.com/channel/UCmXH_moPhfkqCk6S3b9RWuw/join 📚 Get a copy of my books: Think Like a Nobel Prize Winner, with life changing interviews with 9 Nobel Prizewinners: https://a.co/d/03ezQFu My tell-all cosmic memoir Losing the Nobel Prize: http://amzn.to/2sa5UpA The first-ever audiobook from Galileo: Dialogue Concerning the Two Chief World Systems: Ptolemaic and Copernican https://a.co/d/iZPi9Un 📺 Watch my most popular videos:📺 Neil Turok https://www.youtube.com/watch?v=Dt5cFLN65fI Frank Wilczek https://youtu.be/3z8RqKMQHe0?sub_confirmation=1 Eric Weinstein vs. Stephen Wolfram https://www.youtube.com/watch?v=OI0AZ4Y4Ip4?sub_confirmation=1 Sir Roger Penrose: https://youtu.be/AMuqyAvX7Wo Sabine Hossenfelder: https://youtu.be/g00ilS6tBvs Avi Loeb: https://youtu.be/N9lUceHsLRw Follow me to ask questions of my guests: 🏄‍♂️ Twitter: https://twitter.com/DrBrianKeating 🔔 Subscribe https://www.youtube.com/DrBrianKeating?sub_confirmation=1 📝 Join my mailing list; just click here http://briankeating.com/list ✍️ Detailed Blog posts here: https://briankeating.com/blog 🎙️ Listen on audio-only platforms: https://briankeating.com/podcast #universe #podcast #briankeating #intotheimpossible #science #astronomy #cosmology #cosmicmicrowavebackground #intotheimpossible #briankeating #AnilAnanthaswamy Learn more about your ad choices. Visit megaphone.fm/adchoices

Transcript

Click on a timestamp to play from that location

0:00.0

Olivia Culpo here to tell you all about the launch of the new Abercrombie spring denim collection,

0:05.5

made the way denim should feel. Their denim has always been a staple in my wardrobe and has a wide range of fits,

0:11.4

styles, and washes. Every jean is available in both their classic fit and viral curve love.

0:17.5

Shop in the app, online, and in stores.

0:34.0

300 years of expertise in every twining sleep blend.

0:43.9

100 hours of craft in every cup. Eight natural ingredients in every sip. One night of winding down in every drop. Your moment of serenity. Brought to you by twining sleep. Twinings. Alive in every drop.

0:57.0

What of the most powerful AI systems we've ever built are succeeding for reasons we still don't understand?

1:04.0

And worse, they may succeed for reasons that might lock us in for the wrong future for humanity.

1:09.0

Today's guest is Anil Ananthaswamy, an award-winning

1:13.5

science writer and one of the clearest thinkers on the mathematical foundations of machine

1:17.8

learning. In this conversation, we're not just talking about new demos or incremental improvements

1:23.0

or dates on new models being released. We're asking even harder questions. Why does the mathematics

1:28.3

of machine learning work at all? How do these models succeed when they suffer from problems

1:33.8

like overparameterization and lack of input training data? Are large language models revealing

1:39.0

deep structure? Or are they just producing very convincing illusions and causing us to face an increasingly AI slop-driven future?

1:47.2

Thank you so much for joining us all the way from Vangelore. This is so exciting.

1:51.1

Well, Brian, thank you very much for having me. It's a pleasure.

1:54.0

It's really a wonderful book. We're going to judge the book by its cover, as I like to do later on.

2:00.4

It's entitled Why Machines Learn?

2:02.8

And the first question I want to ask you, Anil, is I was taught as a physicist, you can never ask why questions.

2:08.5

That's the first word of your title.

2:11.0

What made you want to explore why and not how or what machines learn instead of why.

...

Please login to see the full transcript.

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

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

Copyright © Tapesearch 2026.