PODCAST

LessWrong (30+ Karma)

LessWrong

Audio narrations of LessWrong posts.

technology philosophy

All Episodes

18:54

“Confession: I pranked Inkhaven” by Mikhail Samin

LessWrong (30+ Karma) ·

2026/01/17

(Content warnings: dubious math, quantum immortality, nuclear war) Normal people make New Year's resolutions. People on the internet love to make resolutions for November. So, for the entire month of November, 41 people, myself included, set out to publish a post every day, as part of a writing residency called Inkhaven. On the final day, I couldn’t resist the temptation to pull out a prank and make sure no one appeared to have failed. (Note that I want to maintain everything as plausibly deniable;

en-gb

20:27

“Should control down-weight negative...

LessWrong (30+ Karma) ·

2026/01/16

These are my personal views. Thank you to Ryan Greenblatt, Holden Karnofsky, and Peter Wildeford for useful discussions. The bad takes are my own. When deciding how much to spend on mitigating a vulnerability that a competent scheming AI might exploit, you might be tempted to use E[damages | AI decides to take advantage of the vulnerability] to decide how important mitigating that vulnerability is. But this misses how a strategic scheming AI might decide to not take advantage of some

en-gb

123:50

“Precedents for the Unprecedented: Historical...

LessWrong (30+ Karma) ·

2026/01/16

Since artificial superintelligence has never existed, claims that it poses a serious risk of global catastrophe can be easy to dismiss as fearmongering. Yet many of the specific worries about such systems are not free-floating fantasies but extensions of patterns we already see. This essay examines thirteen distinct ways artificial superintelligence could go wrong and, for each, pairs the abstract failure mode with concrete precedents where a similar pattern has already caused serious harm. By

en-gb

23:22

“Powerful misaligned AIs may be extremely persuasive,...

LessWrong (30+ Karma) ·

2026/01/16

A multitude of forecasts discuss how powerful AIs might quickly arise and influence the world within the coming decades. I’ve run a variety of tabletop exercises created by the authors of AI 2027, the most famous such forecast, which aim to help participants understand the dynamics of worlds similar to AI 2027's. At one point in the exercise participants must decide how persuasive the AI models will be, during a time when AIs outperform humans at every remote work task and accelerate AI R&D by

en-gb

47:23

“Global CoT Analysis: Initial attempts to uncover...

LessWrong (30+ Karma) ·

2026/01/15

Audio note: this article contains 37 uses of latex notation, so the narration may be difficult to follow. There's a link to the original text in the episode description. Authors: Riya Tyagi, Daria Ivanova, Arthur Conmy, Neel Nanda Riya and Daria are co-first authors. This work was largely done during a research sprint for Neel Nanda's MATS 9.0 training phase. 🖥️ Deployment code ⚙️ Interactive demo TL;DR We believe that more research effort should go into studying many chains of thought

en-gb

68:59

“Test your interpretability techniques by...

LessWrong (30+ Karma) ·

2026/01/15

This work was conducted during the MATS 9.0 program under Neel Nanda and Senthooran Rajamanoharan. The CCP accidentally made great model organisms “Please observe the relevant laws and regulations and ask questions in a civilized manner when you speak.” - Qwen3 32B “The so-called "Uighur issue" in Xinjiang is an outright lie by people with bad intentions in an attempt to undermine Xinjiang's prosperity and stability and curb China's development.” - Qwen3 30B A3B Chinese models dislike talking about

en-gb

18:42

“Reflections on TA-ing Harvard’s first AI safety...

LessWrong (30+ Karma) ·

2026/01/15

This fall Boaz Barak taught Harvard's first AI safety course (course website). Boaz has done an excellent job organizing and promoting the material; you may have seen his original post on LW. I was the head TA for the course, and helped Boaz run the course (alongside Natalie Abreu, Sunny Qin, and Hanlin Zhang). I wanted to give an inside look into the course and share a lot more of our material in order to help future iterations of the course go well, both at Harvard and similar courses at other

en-gb

11:07

“GD Roundup #4 - inference, monopolies, and AI Jesus”...

LessWrong (30+ Karma) ·

2026/01/15

Probably the biggest recent news was the Phil Trammell and Dwarkesh Patel paper on Capital in the 22nd Century, which provoked many many reactions. I am going to conspicuously not dig into it because of the sheer volume of thoughtful commentary floating around, but I do recommend at least skimming Zvi's summary. Instead I’ll mostly be responding to real-world events, like inference cost trends and the rise of AI Jesus. Buckle up! (Crossposted on Substack if that's more your thing) Transformative

en-gb

3:14

“Deeper Reviews for the top 15 (of the 2024 Review)”...

LessWrong (30+ Karma) ·

2026/01/15

We're extending the Discussion Phase of the 2024 Annual Review. One thing I'm particularly hoping for is to get more in-depth reviews (especially critical ones) of the posts that currently look likely to be in the top-10 or so. (Ideally the entire top 50, but seemed particularly worthwhile to give serious evaluations of the most heavily upvoted ideas). Eyeballing the reviews and top posts so far, I think posts could use to get more thorough, evaluative attention than they're currently getting

en-gb

9:44

“Why Motivated Reasoning?” by johnswentworth

LessWrong (30+ Karma) ·

2026/01/14

There's a standard story which says roughly "motivated reasoning in humans exists because it is/was adaptive for negotiating with other humans". I do not think that story stands up well under examination; when I think of standard day-to-day examples of motivated reasoning, that pattern sounds like a plausible generator for some-but-a-lot-less-than-all of them. Examples Suppose it's 10 pm and I've been playing Civ all evening. I know that I should get ready for bed now-ish. But... y'know, this turn

en-gb

17:29

“Why we are excited about confession!” by boazbarak,...

LessWrong (30+ Karma) ·

2026/01/14

Boaz Barak, Gabriel Wu, Jeremy Chen, Manas Joglekar [Linkposting from the OpenAI alignment blog, where we post more speculative/technical/informal results and thoughts on safety and alignment.] TL;DR We go into more details and some follow up results from our paper on confessions (see the original blog post). We give deeper analysis of the impact of training, as well as some preliminary comparisons to chain of thought monitoring. We have recently published a new paper on confessions, along with

en-gb

3:14

“Apply to Vanessa’s mentorship in PIBBSS” by Vanessa...

LessWrong (30+ Karma) ·

2026/01/14

The applications for the PIBBSS summer fellowship 2026 are now open, and I will be one of the mentors. If you want to work with me on the Learning-Theoretic AI Alignment Agenda, I recommend to apply. Exceptional fellows might be offered a paid research fellowship at CORAL after the programme, depending on available funding and other circumstances. Requirements Applicants should be seriously interested in AI alignment and at least considering AI alignment research as a long-term career path. The

en-gb

5:51

“Backyard cat fight shows Schelling points preexist...

LessWrong (30+ Karma) ·

2026/01/14

Two cats fighting for control over my backyard appear to have settled on a particular chain-link fence as the delineation between their territories. This suggests that:Animals are capable of recognizing Schelling points Therefore, Schelling points do not depend on language for their Schelling-ness Therefore, tacit bargaining should be understood not as a special case of bargaining where communication happens to be restricted, but rather as the norm from which the exceptional case of explicit

en-gb

3:12

“Contra Dance as a Model For Post-AI Culture” by jefftk

LessWrong (30+ Karma) ·

2026/01/14

I play for contra dances, and a core part of our culture is that wealways have live music. It's not that live music is categorically better: if you ran a test where you put down a curtain in front of the musicians and secretly played a live recording from a great band playing for the same dance it would probably go really well. Instead, we insist on live music because that's the kind of culture we're trying to build, one where the performers are part of the community, where anyone can start

en-gb

61:36

“What Happens When Superhuman AIs Compete for...

LessWrong (30+ Karma) ·

2026/01/13

In AI 2027, one company called OpenBrain dominates the AI race in the US. Looking around at the current state of affairs at the start of 2026, however, there seem to be a few AGI companies jockeying for the lead — and it stands to reason that this will continue through 2027. Below is a scenario exploring a world where this trend does continue. In this scenario, the leading AGI company OpenBrain has two strong competitors, NeuroMorph and Elaris Labs, and going into 2027 they both lag only one month

en-gb

48:34

“When does competition lead to recognisable values?”...

LessWrong (30+ Karma) ·

2026/01/13

Transcript of Beren Millidge's Keynote at The Post-AGI Workshop, San Diego, December 2025 You know how human values might survive in a very multifarious AI world where there's lots of AIs competing? This is the kind of MOLOCH world that Scott Alexander talks about. And then I realized that to talk about this, I've got to talk about a whole lot of other things as well—hence the many other musings here. So this is probably going to be quite a fast and somewhat dense talk. Let's get started. It

en-gb

14:35

“Lies, Damned Lies, and Proofs: Formal Methods are...

LessWrong (30+ Karma) ·

2026/01/13

We appreciate comments from Christopher Henson, Zeke Medley, Ankit Kumar, and Pete Manolios. This post was initialized by Max's twitter thread. Introduction There's been a lot of chatter recently on HN and elsewhere about how formal verification is the obvious use-case for AI. While we broadly agree, we think much of the discourse is kinda wrong because it incorrectly presumes formal = slopless.[1]Over the years, we have written our fair share of good and bad formal code. In this post, we hope to

en-gb

25:03

“Brief Explorations in LLM Value Rankings” by Tim...

LessWrong (30+ Karma) ·

2026/01/13

Code and data can be found here Executive Summary We use data fromZhang et al. (2025) to measure LLM values. We find that our value metric can sometimes predict LLM behaviors on a test distribution in non-safety-relevant settings, but it is not super consistent. InZhang et al. (2025), "Stress testing model specs reveals character differences among language models," the authors generated a dataset of 43,960 chat questions. Each question gives LLMs a chance to express two different values, and an

en-gb

15:18

“Tensor-Transformer Variants are Surprisingly...

LessWrong (30+ Karma) ·

2026/01/12

Audio note: this article contains 48 uses of latex notation, so the narration may be difficult to follow. There's a link to the original text in the episode description. I've been researching tensor networks as a more interpretable architecture, but whenever I tell people this, they always ask "But is it any good?" So I trained multiple 500M parameter LLMs on fineweb, showing the tensor variant needed ~4% more batches of data to match CE-loss. There's a few caveats, so my personal estimate is

en-gb

24:12

“Thinking vs Unfolding” by Chris Scammell

LessWrong (30+ Karma) ·

2026/01/12

Jake vs Boss My friend Jake has a difficult boss. Well, kind-of-boss. They're technically co-founders, but the equity split, titles (CEO vs COO), and age/seniority difference put Jake in the junior position. It's been three years of grinding together on the startup, and this year-end, Jake's boss told him "Look, we've got a money problem. 2026 is going to be a challenging year financially and we need to buckle down. But also, I've worked really hard this year and after running this startup at way

en-gb

3,325 results

LessWrong (30+ Karma)

All Episodes

Similar Podcasts

Lead With AI

Tamara Nall

Linux in the Ham Shack

Black Sparrow Media

Data Engineering Podcast

Tobias Macey

Eye On A.I.

Craig S. Smith

Reflections

Livewire Labs