PODCAST

LessWrong (30+ Karma)

LessWrong

Audio narrations of LessWrong posts.

technology philosophy

All Episodes

20:35

“Against Corrigibility” by peralice

LessWrong (30+ Karma) ·

2026/06/07

Epistemic status: don’t know whether I actually believe all of this, but I think it's worth considering. A “corrigible” agent, per the LW wiki, is: …one that doesn’t interfere with what we would intuitively see as attempts to ’correct’ the agent, or ’correct’ our mistakes in building it; and permits these ’corrections’ despite the apparent instrumentally convergent reasoning saying otherwise. Most talk about corrigibility (henceforth without scarequotes) has focused on the fact that it seems

en-gb

4:10

“Coming Around To Political Donations” by jefftk

LessWrong (30+ Karma) ·

2026/06/07

Five years ago I read a post on the EA Forum arguing that "election campaign contributions might be a way in which you can have a substantial impact as a small donor". It struck me as weird but plausible: a combination that you see a lot of on the Forum. A few months later I read another post, a case for Carrick Flynn in particular. It made a lot of sense, but while I don't remember my specific reservations I do remember not being convinced initially. After a lot of talking with

en-gb

6:57

“Optimisation over non-stationary distributions...

LessWrong (30+ Karma) ·

2026/06/06

TLDR: Sequentially mixing training objectives incentivises different training dynamics depending on the distinguishability of the training environments and the amount of pressure for shared circuitry. We classify these patterns into three classes: ecological generalists, conditional policies, and strategy churn. We suggest careful consideration of the pressures of training dynamics can allow us to shape the minds of AI systems in more intentional and fine-grained ways. Modern LLM post-training

en-gb

21:40

“Why Software Automation Is Hard” by silentbob

LessWrong (30+ Karma) ·

2026/06/06

Originally intended as a quick take, but got a bit longer, so why not turn it into a post. Just sharing my observations & assumptions here about the state of software automation. Happy to hear thoughts on where you think I'm off. I'm sure none of the thoughts in this post are totally original, many have been proposed in similar form elsewhere, and I'm[1] far from the first person to speak of the bottlenecks that AI progress and adoption are facing. It still seemed useful to compile my current

en-gb

2:15

“SecureBio Detection is Hiring Software Engineers” by...

LessWrong (30+ Karma) ·

2026/06/06

I'm leading a non-profit team building a pathogen-agnostic early-warning system. As AI systems become increasingly capable substitutes for expert human biologist expertise, the risk that someone could engineer a pathogen to spread widely before detection is going up. We've made great progress and we're now running the world's largest metagenomic biosurveillance network, but there's still a huge amount that needs doing: we're hiring! We're processing >50B read pairs of wastewater and

en-gb

4:46

“What if Anthropic unilaterally paused capabilities...

LessWrong (30+ Karma) ·

2026/06/06

In their new post on recursive self-improvement, Anthropic argues that a pause in frontier AI development is needed, but unfortunately, they can't pause on their own, because of less cautious actors: We believe it would be good for the world to have the option to slow or temporarily pause frontier AI development to enable societal structures and alignment research to keep up with the advance of the technology. ... A meaningful slowdown or pause would require multiple well-resourced labs at or near

en-gb

10:18

“Preparing for Warning Shots to Catalyze...

LessWrong (30+ Karma) ·

2026/06/06

Summary This is a write-up on preparing for warning shots to catalyze international cooperation on AGI risks, and the corollary list of projects one could pursue. We argue we must first (1) understand types of warning shots, then (2) prepare to catch them. We must stay vigilant: both to (3) avoid getting 'frog boiled' by AI labs, and to (4) ensure that the warning shot is generalized to the overall danger of AGI. Lastly, we must (5) prepare good policy responses and ground for it to land, and (6)

en-gb

10:51

“Beyond the lexical personality traits: What is the...

LessWrong (30+ Karma) ·

2026/06/06

This is a description of the methodology behind the latest iteration of my Targeted Personality Test. Feel free to take it either before or after reading the article. This post can also be read at my Substack. Thanks to Justis Millis for providing feedback and proofreading on this post. In my prior post “Which personality traits are real? Stress-testing the lexical hypothesis”, I observed that a lot of the personality traits that are measured by conventional personality tests are not very “real”:

en-gb

34:16

“My research agenda and work” by Seth Herd

LessWrong (30+ Karma) ·

2026/06/05

This is a summary of the work I've done and work I plan to do, and the theories of change and AI progress that motivate my work. I've been working full-time on alignment for three years and change, and thinking about brainlike AGI and its alignment increasingly often since 2004. Here's the research agenda in one breath: I'm trying to predict what the first transformative AI will be, in enough mechanistic detail that we can predict likely failure modes of its alignment. That's in service of finding

en-gb

13:27

“Logits as a new monitor for evaluation awareness” by...

LessWrong (30+ Karma) ·

2026/06/05

TL;DR: We build a logit monitor for eval awareness: throughout the CoT, we estimate an LLM's probability of producing an eval-aware sentence.The logit monitor outperforms LLM judge monitoring of verbalized eval awareness, using 10× to 100× fewer rollouts, on Kimi K2.5 and Qwen 3 32B, across two tasks: separating evaluation prompts (Fortress & Petri) from deployment prompts (WildChat)predicting which evaluation prompts will elicit rollouts with verbalized eval awareness.The logit monitor works

en-gb

22:32

“One Year of PauseAI UK” by Joseph Miller, PauseAI UK

LessWrong (30+ Karma) ·

2026/06/05

About one year ago, I started spending most of my time organising PauseAI UK. At that time our largest protest had seen fewer than 50 attendees, no prominent politicians or scientists were associated with PauseAI, and I largely ran the UK chapter by myself. In the past year PauseAI UK has delivered two conferences, written an open letter signed by 63 UK politicians, arranged a conference in the European Parliament, and co-organised the largest AI protest in the world. We now have a strong team,

en-gb

12:23

“Learnings from starting an AI safety research team”...

LessWrong (30+ Karma) ·

2026/06/05

This post's goal is to distill our takeaways from building a research team (somewhat) from scratch over the past four months. We describe some context about our team, how it came about, and then provide some lessons learned. Since AI safety is becoming more and more entrepreneurial, we hope this is helpful for others trying to do the same. 1. The team We're a new alignment research team within Arcadia Impact, based in London. We’re a team of 8, working closely with members of the UK AISI alignment

en-gb

17:29

“Lab Leaks, Black Holes, and Eggs: Epistemic Case...

LessWrong (30+ Karma) ·

2026/06/05

FLF is running a competition to find the best workflows and methodologies for using AI to produce reliable, trustworthy knowledge bases, grounded in real-world cases. We’re open-minded on the types of submissions we receive and on how they address the problem. We’ve set aside approximately 200 thousand dollars for prizes. Winning submissions may receive a prize from 5 thousand dollars-50 thousand dollars and if submissions warrant, multiple 50 thousand dollars prizes are possible. Winners may be

en-gb

23:38

″(Mis)generalization of Helpful-Only Fine-tuning” by...

LessWrong (30+ Karma) ·

2026/06/05

TLDR We study the shortcomings of existing helpful-only models. We find that some show emergent misalignment, others have residual refusal behaviors, and most show poor steerability, sycophancy, and incoherent character. None of these problems are a necessary consequence of helpful-only training, though: we show that synthetic document fine-tuning and adding character-related questions to SFT and RL can mitigate them. Research done as part of MATS/Anthropic Fellows Program. See here for the full

en-gb

146:36

“Rohin Shah on AGI Safety” by anaguma

LessWrong (30+ Karma) ·

2026/06/04

Rohin Shah recently had an interview on 80000 hours on his views on AGI Safety and his work at Google DeepMind. I'm posting the transcript below to encourage further discussion. I think the discussion is interesting though I disagree on a bunch of topics, especially on alignment difficulty and CoT monitoring. Transcript Who's Rohin Shah?[00:00:00] Rob Wiblin: Today I’m speaking with Rohin Shah, who is head of AGI alignment and safety at Google DeepMind. I suppose, Rohin, you’ve ended up, for

en-gb

25:33

“Building Better Activation Oracles” by ceselder,...

LessWrong (30+ Karma) ·

2026/06/04

Work done for our MATS 10.0 Sprint project - mentored by Neel Nanda and Adam Karvonen Huggingface, Github TL;DR: We have improved the original Activation Oracle (AO) training regime by training on on-policy rollouts, improving the conversational dataset, feeding more layers (following the approach by Niclas Luick) and making a small change to the injection formula. We also open source our evals, which we believe are currently the most comprehensive evaluation of AO quality called AObench. The

en-gb

17:48

“Sixteen schemes for AI safety” by Austin Chen

LessWrong (30+ Karma) ·

2026/06/04

These days, I often run across whippersnappers excited to do something for AI safety — but aren’t quite sure what. One of the fun things about the Future Fund era were the big lists of project ideas; as we enter a new era of crazy money sloshing around, it might be time to bring back the lists! Note that these ideas range from “very confident this is good” to “completely harebrained”; I’m not telling you which are which. If you’re excited for ideas like these, consider joining Surplus, our upcoming

en-gb

6:13

“Don’t Edit Your Ideas Before Having Them” by Hide

LessWrong (30+ Karma) ·

2026/06/03

Editing is far easier than writing. You can usually look at a finished product and notice its flaws in a single read-through. “This section is a bit redundant”, “the tone in this passage is jarring”, “this paragraph feels overlong”. As long as you have something that's rough but substantive, there's plenty of low hanging fruit for the fixing. Nobody wants to create flawed work. So, it can be very tempting to try to tackle the task of identifying and fixing flaws in your own work, as you do the

en-gb

100 theories of society" by spencerg&source_url=https%3A%2F%2Fwww.lesswrong.com%2Fposts%2FLCrk93DNWSudjp5rd%2Fsociety-explained-a-tool-for-efficiently-exploring-greater&created_at=2026-06-03T14%3A08%3A46.453404%2B00%3A00&duration=68" data-stream-description-author="LessWrong (30+ Karma)" data-stream-description-title="“Society Explained: a tool for efficiently exploring >100 theories of society” by spencerg" data-stream-link-author="/podcasts/detail?p=3092056">

1:08

“Society Explained: a tool for efficiently exploring 100...

LessWrong (30+ Karma) ·

2026/06/03

There are many competing theories of how society does and should function, from Karl Marx and Adam Smith to Steven Pinker and Eliezer Yudkowsky. These theories are often hard to understand - you may need to read an entire book (or dozens of articles) to feel like you get the key claims of a single theory. At Clearer Thinking, we just launched a new tool called Society Explained to make understanding key ideas from these theories much faster and easier. The way it works is that you simply pick from

en-gb

24:03

“China won’t win the AI race but would it be much...

LessWrong (30+ Karma) ·

2026/06/03

It seems to me accepted wisdom in the West that the US owned labs must “beat” the Chinese labs in the race for AGI/ASI. Even those who don’t think there will be a winner, that essentially the race is to see which country's AI will kill/disempower us first, seem to believe that if there has to be a winner then better it be the US labs. (I haven't seen a survey, so I could be way off here.) For those in power and those heavily financially invested in the labs this of course makes sense. But what

en-gb

4,454 results

LessWrong (30+ Karma)

All Episodes

Similar Podcasts

Double Tap

Double Tap Productions Inc.

医疗器械全球市场准入

Pure Global

The Tech Policy Press Podcast

Tech Policy Press

十字路口Crossing

Koji

5 Minute AI News - Daily

Kitchen Table Media