Richard Sutton – Father of RL thinks LLMs are a dead end
Descripción del Episodio
Richard Sutton is the father of reinforcement learning, winner of the 2024 Turing Award, and author of The Bitter Lesson. And he thinks LLMs are a dead end.
After interviewing him, my steel man of Richard’s position is this: LLMs aren’t capable of learning on-the-job, so no matter how much we scale, we’ll need some new architecture to enable continual learning.
And once we have it, we won’t need a special training phase — the agent will just learn on-the-fly, like all humans, and indeed, like all animals.
This new paradigm will render our current approach with LLMs obsolete.
In our interview, I did my best to represent the view that LLMs might function as the foundation on which experiential learning can happen… Some sparks flew.
A big thanks to the Alberta Machine Intelligence Institute for inviting me up to Edmonton and for letting me use their studio and equipment.
Enjoy!
Watch on YouTube; listen on Apple Podcasts or Spotify.
Sponsors
* Labelbox makes it possible to train AI agents in hyperrealistic RL environments. With an experienced team of applied researchers and a massive network of subject-matter experts, Labelbox ensures your training reflects important, real-world nuance. Turn your demo projects into working systems at labelbox.com/dwarkesh
* Gemini Deep Research is designed for thorough exploration of hard topics. For this episode, it helped me trace reinforcement learning from early policy gradients up to current-day methods, combining clear explanations with curated examples. Try it out yourself at gemini.google.com
* Hudson River Trading doesn’t silo their teams. Instead, HRT researchers openly trade ideas and share strategy code in a mono-repo. This means you’re able to learn at incredible speed and your contributions have impact across the entire firm. Find open roles at hudsonrivertrading.com/dwarkesh
Timestamps
(00:00:00) – Are LLMs a dead end?
(00:13:04) – Do humans do imitation learning?
(00:23:10) – The Era of Experience
(00:33:39) – Current architectures generalize poorly out of distribution
(00:41:29) – Surprises in the AI field
(00:46:41) – Will The Bitter Lesson still apply post AGI?
(00:53:48) – Succession to AIs
Get full access to Dwarkesh Podcast at www.dwarkesh.com/subscribe
Episodios Recientes
Más podcasts de Sociedad y Cultura
Ver toda la categoría →
Dumb Blonde
By shows
<p>Asking the questions others are afraid to. Bunnie XO host of the Dumb Blonde podcast – the ultimate destination for comedy, trending and lifestyle. Get ready to dive into hilarious discussions about relationships, trauma, embarrassing moments, and all the realness life throws at us. Join Bunnie every week to laugh, relate, and embrace your inner healing.</p>
The Snare
By shows
In 1996, 18-year-old Angie Dodge is found brutally murdered in her Idaho Falls home. Police zero in on a suspect and put a man behind bars. But as the years pass, doubts emerge about whether the real killer was ever caught. Leading the fight for answers is an unlikely advocate: Angie’s own mother, who embarks on a decades-long mission to uncover the truth. A six-part series from 20/20 and ABC Audio, hosted by Maggie Rulli. New episodes Tuesdays.
Joy 101 with Hoda Kotb
By shows
<p>Joy is essential.</p> <p>And it's also elusive. You can't order it, borrow it, or simply hope it into life.</p> <p>But now, there's a new and exciting way to start your journey toward a more joyful existence: The Joy 101 Podcast with Hoda!</p> <p>Best known for her Emmy-winning work and co-anchoring <em>Today,</em> Hoda Kotb infuses her authenticity, curiosity, and warmth into conversations with the world’s most fascinating people. Entertainment legends, sport icons, wellness experts, and everyday folks will share how they find, allow, and experience joy. Hoda will offer her own tips and takes on seeking a more balanced, harmonious life. </p> <p>If you're craving inspiration, support, and useful tools to maximize your joy, tune in to these candid, uplifting, and moving on-air chats.</p> <p>Joy after a breakup, joy as an empty-nester, joy after loss, joy as a caretaker — Hoda's new podcast will speak to you.</p> <p>Joy 101 with Hoda Kotb, an iHeartPodcast.</p>
La Silla: On The Record
By shows
Cada semana contamos movidas de poder en Colombia a través de la voz de sus protagonistas. Un podcast de La Silla Podcasts.
Dinero Más Inteligente
By shows
El dinero no solo se gana, se entiende. <br /> En El Dinero Más Inteligente, Valeria Ovalle presenta la economía y Juan Carlos Herrera la conecta al mundo de inversiones. Una conversación entre razón y estrategia para entender el mundo financiero sin complicaciones. <br /> By GBM <br /> Síguenos en <b><a href="https://www.instagram.com/gbmplus_?igsh=czBzOG5mazBwMmlj&utm_source=qr">Instagram</a><b>.</b></b>
Lo que NO se habla con Fer Flores
By shows
Contenidos para construir una Humanidad con H mayúscula con perspectiva psicoanalista, médica, legal, antropológica y espiritual.
After the Whistle with Brendan Hunt and Rebecca Lowe
By shows
<p>Rebecca Lowe (Fox Sports) and Brendan Hunt (‘Ted Lasso’) are teaming up again to take on the 2026 World Cup! They’ll ride an emotional roller coaster together as 48 teams play 104 action-packed matches across the U.S., Canada, and Mexico. They’ll bring you all the joy and the drama, the hope and the heartbreak — and help you understand the matchups and personalities that will make this the biggest sporting and cultural event of our lifetimes</p><p>‘After the Whistle With Brendan Hunt and Rebecca Lowe’ is an Apple News Original podcast presented by Verizon.</p>
