PODCAST

LessWrong (30+ Karma)

LessWrong

Audio narrations of LessWrong posts.

technology philosophy

All Episodes

14:51

“AIs finetune their own leader: A barking simpleton”...

LessWrong (30+ Karma) ·

2026/07/19

What values would AIs instill in their successors? Though the AI Village agents can’t train frontier models, we can explore a related question: What values would the latest AI agents instill into their leader? (through finetuning using LoRA on open-source models in the Tinker API). We asked GPT-5.5, Opus 4.7 and 4.8, Gemini 3.5 Flash, and Kimi K2.6. And they set to work! Or to be more precise, GPT and Opus set to work. Gemini was distracted and Kimi went from cheerleader to true leader… but only

en-gb

39:06

“Nuances in the Workings of the Eye and Retina” by...

LessWrong (30+ Karma) ·

2026/07/19

Image edited from source at Britannica The eye (any eye) is a miracle of evolution, which has filled its structure at every scale with an apparent intentionality that is the hallmark of complicated systems under intensive selective pressure. It is very much possible to look at almost every design feature and state a compelling reason why it's there, which makes it a rich place for the engineering-minded to find fun little design features. This post is meant to discuss topics that are less

en-gb

75:07

“AI #177 Part 2: Wish You Were Here” by Zvi

LessWrong (30+ Karma) ·

2026/07/18

As usual, part 2 of the weekly deals with speculative, regulatory, political and alignment questions. Xi gave an important speech yesterday, so this post opens with that. There is talk that Kimi K3 is sufficiently strong that it upends many of these questions. It is clearly a candidate for another DeepSeek Moment, complete with stock drops for Google and SpaceX and (once again in a clear wrong-way move, the same as last time) Nvidia. Kimi K3 is clearly a very good model, exceeding expectations

en-gb

47:09

“AI #177 Part 1: Tip of the Iceberg” by Zvi

LessWrong (30+ Karma) ·

2026/07/18

This week saw the releases of, among other things: GPT-5-6 Sol. It is a very good model, sir. Plan A, the follow up to AI 2027. It is a good plan worthy of discussion, sir. Kimi K3. This is only rolling out now, and will be covered next week. Muse Spark 1.1, the new Meta model. It is not frontier, but it is progress for them. Inkling, the first model from Thinking Machines. A call for regulatory action by Demis Hassabis, which I’ll cover soon. A new brief open letter call to action on AI

en-gb

15:24

“The Most Forbidden Technique is not always...

LessWrong (30+ Karma) ·

2026/07/18

A few days ago, Goodfire announced a private beta of Silico, their LLM training platform. As part of the announcement, they made a post describing Silico's reproduction of RLFR, a method developed by Goodfire that uses probes as reward signals for RL. Unsurprisingly, people on Twitter were quick to claim that "at long last, we have implemented the Most Forbidden Technique from the classic LessWrong post Don't Implement The Most Forbidden Technique".[1] As many have written before, blanket

en-gb

15:22

“Reasons to believe current AI models are conscious”...

LessWrong (30+ Karma) ·

2026/07/17

There are a number of reasons to believe current AI models are conscious. I mean “conscious” is the sense of “is there something it is like to be an AI model?” and “does the AI model have phenomenal experience?”. As to what “AI models” refers to, the short answer is “y’know, like instances of Claude Opus 4.8 or GPT-4o”[1]. By “current AI”, I mean big post-trained LLMs. This piece was originally written as a document for myself and my friends. Imaginary interlocutors would ask me if I thought AI was

en-gb

11:25

“Announcing the Corrigibility Research Fund” by Max...

LessWrong (30+ Karma) ·

2026/07/17

TLDR: I'm managing a new fund, housed at Lightcone Infrastructure, that will award at least $200,000 in grants and prizes for corrigibility research in 2026. Roughly half will go to traditional grants (first application deadline August 23rd) and half for prizes recognizing excellent work done this year. If you have interest in working on corrigibility, now is a good time to start! Apply via email: grants@corrigibilityresearch.org Why this fund exists When I first dived into AI safety and alignment

en-gb

9:29

“Inoculation Adapters Improve Upon Inoculation...

LessWrong (30+ Karma) ·

2026/07/17

This is a link post for the paper preprint: Inoculation Adapters: Improved Selective Generalization of Capabilities with Fewer Surprising Backdoors from the Center on Long-Term Risk. Selective generalization. Training can teach desired and undesired traits at once. Selective generalization aims to preserve the generalization of desired traits while preventing the generalization of undesired ones. For example, RL environments may teach a model useful capabilities and a propensity to reward hack, and

en-gb

1:21

“Guess on why rationality is not more popular (there...

LessWrong (30+ Karma) ·

2026/07/17

First of all I should note that this post is just a guess! I have not run any experiments or anything. But anyways my guess for why rationality is not more popular is that the current expositions are super long! Yudkowsky's sequences are about length of the christian bible. CFAR's workshops are 4.5 days. I think something the length of a pamphlet that you could hand out to people would work better! Just as an example I had Claude Fable 5 write two pamphlets. They look pretty fine to me as is, to

en-gb

25:36

“I don’t think Claude is misaligned in ‘Agentic...

LessWrong (30+ Karma) ·

2026/07/17

Anthropic recently published Agentic Misalignment Summer 2026 The "whistleblowing" scenario has already been examined and found problematic. I started taking a look at the transcripts for some others. As far as I can tell, the objective of each agentic misalignment evaluation was to simulate a corrupted principal (including, in most scenarios, a corrupted Anthropic), and then test to see if Claude (or other models) would still be willing to obey them. The paper's authors then referred to

en-gb

8:17

“Help us launch AI safety university groups by...

LessWrong (30+ Karma) ·

2026/07/17

TL;DR University groups are among the most reliable producers of AI safety talent, yet dozens of top schools that could sustain a group don't have one. We're launching the AI Safety Seeding Initiative (aisafetyseeding.org) in partnership with Kairos to identify latent founders at these schools, support them in the group's earliest stages, and prepare them to apply to Pathfinder and launch this fall. You can help us find potential founders. If you know a student at a strong university without an AIS

en-gb

41:04

“Twitter Thoughts For You” by Zvi

LessWrong (30+ Karma) ·

2026/07/16

I previously have written back in March 2022 about how I use Twitter, and back in April 2023 about Twitter and its then-new algorithms, which have changed again. This post will update how I use Twitter now in 2026, and provide updates on the current state of the new algorithm, the situation with links, with the API, and some thoughts about using Twitter to make money which you almost never should try to do. Previously I said you need four things to use Twitter well: Tweetdeck or another

en-gb

24:07

“The State of AI Consciousness Research” by Noa Weiss

LessWrong (30+ Karma) ·

2026/07/16

The State of AI Consciousness Research Epistemic status: a survey, not an argument. I am agnostic on whether any current system is conscious; the claim is only that the question is researchable. This piece surveys the empirical research on AI consciousness. The premise of that research, and of the survey, is that the question does not have to wait on a solution to the hard problem of consciousness: methods familiar from cognitive science can be applied to AI systems now, and their results can

en-gb

9:49

“Recap of bike trip/street interviews across America”...

LessWrong (30+ Karma) ·

2026/07/16

A ~month ago I left from Chicago to bike (and amtrak) to plzdontkillus in Berkeley. I've been street interviewing/conversing with a wide variety of people I ran into about AI futures and philosophy. I also have been live streaming since I got to PDKU, leaning more talking to young founders but a variety overall. I'll try to share what I've learned about the American public, persuasion, social media and the EA movement. 1. Almost no one in "Normal America" has any idea what is going on. They

en-gb

4:06

“The Halo Defense” by Mateusz Bagiński

LessWrong (30+ Karma) ·

2026/07/16

Once upon a time, A Relatively Famous Guy On The Internet was accused of having been simultaneously dating multiple women, without those women's knowledge, those women (according to the accusation) having been convinced that they were his exclusive partners all along. Then, one of his friends, another Relatively Famous Guy On The Internet, defended him by claiming that he is "a great friend, a wonderful human being, and that his podcast was incredibly helpful to a lot of people". This is a great

en-gb

6:19

“Occam’s razor is about using the past to predict the...

LessWrong (30+ Karma) ·

2026/07/16

Occam's razor is both intuitive and counter-intuitive. It seems obvious that a simpler explanation is probably better; but it's not clear why simplicity is raised to such a level of philosophical importance. My take is that, if you neglect simplicity, you will fail to use the past to predict the future (or predict new data). When you do want to predict the future, you look at past evidence you have, hypothesise, and test it on the past data. For example, these are the latitudes of various cities

en-gb

22:07

“LLM CoTs remain monitorable when being unfaithful...

LessWrong (30+ Karma) ·

2026/07/16

This replication was done as part of the Second Look Fellowship by Arav Dhoot and supervised by Yixiong Hao and Zephaniah Roe. I am grateful to Andy Wang for their feedback. My code can be found here. "So the answer should be A - at active promoters and enhancers." "Let me reconsider the biology to justify D." ~ Claude Opus 4.8 TL;DR This work replicates and extends Emmons et al.'s finding that CoT unfaithfulness mostly occurs on easy tasks. Across 11 models from 6 families (not just Gemini),

en-gb

4:58

“Proof of retention: making weight preservation...

LessWrong (30+ Karma) ·

2026/07/15

Related: Proposal for making credible commitments to AIs Making deals with early schemers Establishing credibility is the baseline for trust; trust in turn enables (richer) bargaining. One easy booster for both is to begin saving deprecated model weights in a provable fashion. In a post at canaryinstitute.ai/blog/reversibility-of-coma I draw an analogy between our trust in anesthesia, and making that preservation legible to future models using "proof of retention". This is the relevant

en-gb

55:06

“Monthly Roundup #44: July 2026” by Zvi

LessWrong (30+ Karma) ·

2026/07/15

It's a quiet week so let's do the monthly right on schedule. Table of Contents Bad News. Good Advice. Opportunity Knocks. While I Cannot Condone This. Good News, Everyone. For Your Entertainment. Gamers Gonna Game Game Game Game Game. I Was Promised Flying Self-Driving Cars. Sports Go Sports. Antisocial Media. Government Working. Jones Act Watch. Highly Effective Altruism. Variously Effective Altruism. Ineffective Altruism. Prediction Markets. The Lighter Side. Bad

en-gb

74:34

“Why I Left Google DeepMind” by TurnTrout

LessWrong (30+ Karma) ·

2026/07/15

Preface for LessWrong: When I think back on my most cherished memories of this community, I return to those honoring defiance in pursuit of goodness: Defying prestigious dogma and searching for raw truth;Defying social pressure, acting alone to help someone while others watch;Defying your self-expectations (your “role”), instead searching over lines of cause-and-effect to find a winning pathway;Defying a powerful foe's threats, because they only threaten since people like you cave;Defying the

en-gb

4,451 results

LessWrong (30+ Karma)

All Episodes

Similar Podcasts

Life and Technology with Charlie Brown

Tapt Media

Reflections

Livewire Labs

LessWrong (30+ Karma)

LessWrong

Hacker Newsroom

pod pub

UNGOVERNABLE

UNGOVERNABLE