pod.link/1698192712
pod.link copied!
LessWrong (30+ Karma)
LessWrong (30+ Karma)
LessWrong

Audio narrations of LessWrong posts.

Listen now on

Apple Podcasts
Spotify
Overcast
Podcast Addict
Pocket Casts
Castbox
Podbean
iHeartRadio
Player FM
Podcast Republic
Castro
RSS

Episodes

“The vision of Bill Thurston” by TsviBT

PDF version. berkeleygenomics.org. William Thurston was a world-renowned mathematician. His ideas revolutionized many areas of geometry and topology[1]; the... more

29 Mar 2025 · 8 minutes
“Tormenting Gemini 2.5 with the [[[]]][][[]] Puzzle” by Czynski

Includes a link to the full Gemini conversation, but setting the stage first: There is a puzzle. If you... more

29 Mar 2025 · 5 minutes
“Softmax, Emmett Shear’s new AI startup focused on ‘Organic Alignment’” by Chipmonk

A new AI alignment player has entered the arena. Emmett Shear, Adam Goldstein and David Bloomin have set up... more

28 Mar 2025 · 2 minutes
“The Pando Problem: Rethinking AI Individuality” by Jan_Kulveit

Epistemic status: This post aims at an ambitious target: improving intuitive understanding directly. The model for why this is... more

28 Mar 2025 · 27 minutes
“Gemini 2.5 is the New SoTA” by Zvi

Gemini 2.5 Pro Experimental is America's next top large language model. That doesn’t mean it is the best model... more

28 Mar 2025 · 27 minutes
“AI #109: Google Fails Marketing Forever” by Zvi

What if they released the new best LLM, and almost no one noticed? Google seems to have pulled that... more

28 Mar 2025 · 1 hour, 14 minutes
“Explaining British Naval Dominance During the Age of Sail” by Arjun Panickssery

The other day I discussed how high monitoring costs can explain the emergence of “aristocratic” systems of governance: Aristocracy... more

28 Mar 2025 · 8 minutes
“Tracing the Thoughts of a Large Language Model” by Adam Jermyn

[This is our blog post on the papers, which can be found at https://transformer-circuits.pub/2025/attribution-graphs/biology.html and https://transformer-circuits.pub/2025/attribution-graphs/methods.html.] Language models like... more

27 Mar 2025 · 22 minutes
“Third-wave AI safety needs sociopolitical thinking” by Richard_Ngo

At EA Global Boston last year I gave a talk on how we're in the third wave of EA/AI... more

27 Mar 2025 · 47 minutes
“Mistral Large 2 (123B) exhibits alignment faking” by Marc Carauleanu, Diogo de Lucena, Gunnar_Zarncke, Cameron Berg, Judd Rosenblatt, Mike Vaiana, AE Studio

Summary We wanted to briefly share an early takeaway from our exploration into alignment faking: the phenomenon appears fairly... more

27 Mar 2025 · 3 minutes
Claim your free pod.link
Customize to match your brand
Claim a memorable URL
Add your own Google Analytics
Confirm Ownership

To claim this podcast, you must confirm your ownership via the email address located in your podcast’s RSS feed (pod****@type3.audio). If you cannot access this email, please contact your hosting provider.