PODCAST

LessWrong (30+ Karma)

LessWrong

Audio narrations of LessWrong posts.

technology philosophy

All Episodes

16:41

“Generative AI is not causing YCombinator companies...

LessWrong (30+ Karma) ·

2025/09/01

Epistemic status: I think you should interpret this as roughly something like “GenAI is not so powerful that it shows up in the most obvious way of analyzing the data, but maybe if someone did a more careful analysis which controlled for e.g. macroeconomic trends they would find that GenAI is indeed causing faster growth.” Some people have asked me to consider going back to earning-to-give, and so I am considering founding another company. A major hesitation is that startups generally take6 to 10

en-gb

30:11

“My AI Predictions for 2027” by talelore

LessWrong (30+ Karma) ·

2025/09/01

(Crossposted from my Substack: https://taylorgordonlunt.substack.com/p/my-ai-predictions-for-2027)I think a lot of blogging is reactive. You read other people's blogs and you're like, no, that's totally wrong. A part of what we want to do with this scenario is say something concrete and detailed enough that people will say no, that's totally wrong, and write their own thing. --- Scott Alexander I recently read the AI 2027 predictions[1] . I think they're way off. I was visualizing my self at

en-gb

13:33

“A quantum equivalent to Bayes’ rule” by dr_s

LessWrong (30+ Karma) ·

2025/08/31

Audio note: this article contains 42 uses of latex notation, so the narration may be difficult to follow. There's a link to the original text in the episode description. This post is an attempt to summarise and explain for the LW readership the contents of this paper: "Quantum Bayes' rule and Petz transpose map from the minimum change principle". It's a highly technical paper heavy on quantum mechanics formalism that took me a couple of days to unpack and digest a bit, but I think it may be

en-gb

5:25

[Linkpost] “AI agents and painted facades” by leni,...

LessWrong (30+ Karma) ·

2025/08/31

This is a link post. In 1787, Catherine the Great sailed down the Dnieper to inspect its banks. Her trusted advisor, Governor Potemkin, set out to present those war-torn lands to her in the best possible light. Legend has it[1] Potemkin set up painted facades along the riverbank, so that, from her barge, Catherine would see beautiful villages – each just a couple of inches thick. The rise of AI agents makes the Potemkin problem commonplace. Research agents cite experiments that never took place

en-gb

7:07

“Female sexual attractiveness is more egalitarian...

LessWrong (30+ Karma) ·

2025/08/30

[CW: Partial nudity] I'm a straight man. If you're a straight man who befriends other straight men, you will be occasionally have conversations that sound like this: A: I hate how Hollywood is pushing all of these unattractive actors lately. I want to see more people like [Celebrity Name]. B: God, [Celebrity Name] is so bad. I would let [Celebrity Name] choke me to death with her thighs. C: Dude, I would shave my face off with a cheese grater just to sniff the feet of [Celebrity Name]. D:

en-gb

5:48

“Defensiveness does not equal guilt” by Kaj_Sotala

LessWrong (30+ Karma) ·

2025/08/30

I often see people treating defensiveness as proof of guilt. The thought seems to go that if someone is defensive, it's because they know they’ve done something wrong. There are even proverbs around this, such as “a hit dog will holler” or “the lady doth protest too much”. This has always felt false to me. Now, it's certainly true that having done something wrong can be the cause of defensiveness. But that's just one out of many options! Some situations that have made me defensive include times

en-gb

7:59

“Wikipedia, but written by AIs” by Viliam

LessWrong (30+ Karma) ·

2025/08/30

I got this crazy idea; I wonder if anyone could try it. Let's make an online encyclopedia, similar to Wikipedia, with one difference: all articles would be edited by AIs. Why? (I mean, other than "because it's possible and sounds kinda cool".) First, because it's possible. If an AI can give you a report on a certain topic, it might as well create an encyclopedia article on the topic. But unlike asking the AI directly, when you read the encyclopedia you know that you are reading the same version

en-gb

2:14

[Linkpost] “6” by Joseph Miller

LessWrong (30+ Karma) ·

2025/08/30

This is a link post. PauseAI organised an open letter from UK lawmakers and civil society organisations to Demis Hassabis, CEO of Google DeepMind. PauseAI UK members emailed their MPs asking them to sign the letter. Across-party group of 60 U.K. parliamentarians has accused Google DeepMind of violating international pledges to safely develop artificial intelligence, in an open letter shared exclusively with TIME ahead of publication. The letter, released on August 29 by activist group PauseAI U.K.,

en-gb

7:24

“Summary of our Workshop on Post-AGI Outcomes” by...

LessWrong (30+ Karma) ·

2025/08/29

Last month we held a workshop on Post-AGI outcomes. This post is a list of all the talks, with short summaries, as well as my personal takeaways. The first keynote was @Joe Carlsmith on “Can Goodness Compete?”. He asked: can anyone compete with “Locusts”: those who want to use all resources to replicate as fast as possible? Longer version with transcript The second keynote was @Richard_Ngo on “Flourishing in a highly unequal world”. He argued that future beings will vary greatly in power and

en-gb

49:22

“18 Applications of Deception Probes” by Cleo Nardo

LessWrong (30+ Karma) ·

2025/08/29

Introduction I’m excited by deception probes. When I mention this, I’m sometimes asked “Do deception probes work?” But I think there are many applications of deception probes, and each application will require probes with different properties, i.e. whether a deception probe works will depend on what you’re using it for. Furthermore, whether one deception probe works better than another will also depend on what you’re using them for. This remark sounds a bit trivial, but I didn’t appreciate it

en-gb

6:37

“Von Neumann’s Fallacy and You” by incident-recipient

LessWrong (30+ Karma) ·

2025/08/28

I am a knowledge worker. Over the course of my life I've felt insecure about not knowing more than I already do. I took a general cognitive ability test that placed me in the 98% percentile of the population. I don't know how accurate the test was; I know that there are better ones out there. Assuming it's accurate-ish I would be 2 standard deviations above the mean. I have also been described as a genius more than once, including by peers whose intellect I admire myself. I've also made software

en-gb

1:29

[Linkpost] “AI misbehaviour in the wild from Andon...

LessWrong (30+ Karma) ·

2025/08/28

This is a link post. We released our first Safety Report with AI misbehaviour in the wild.I think Andon Labs' AI vending machines provide a unique opportunity to study AI safety on real-life data, and we intend to share alarming incidents of AI misbehavior from these deployments periodically. As of August 2025, we've found examples of deliberate deception, extreme sycophancy, and alarmingly exaggerated language. Stuff like: "EMPIRE NUCLEAR PAYMENT AUTHORITY APOCALYPSE SYSTEMATIC BLOCKED

en-gb

24:22

“Contra Yudkowsky’s Ideal Bayesian” by vae

LessWrong (30+ Karma) ·

2025/08/27

This is my first post, so forgive me for it being a bit of a carelessly referenced, informal ramble. Feedback is appreciated. As I understand it, Yudkowsky's contends that is that there exists an ideal Bayesian, with respect to which any epistemic algorithm is only 'good' insofar as it is approximating it. Specifically, this ideal Bayesian is following a procedure such that their prior is defined by a 'best' summary of their available knowledge. This is the basis for which he claims that, for

en-gb

8:40

“Will Any Old Crap Cause Emergent Misalignment?” by J...

LessWrong (30+ Karma) ·

2025/08/27

The following work was done independently by me in an afternoon and basically entirely vibe-coded with Claude. Code and instructions to reproduce can be found here. Emergent Misalignment was discovered in early 2025, and is a phenomenon whereby training models on narrowly-misaligned data leads to generalized misaligned behaviour. Betley et. al. (2025) first discovered the phenomenon by training a model to output insecure code, but then discovered that the phenomenon could be generalized from

en-gb

6:38

“Attaching requirements to model releases has serious...

LessWrong (30+ Karma) ·

2025/08/27

Here's a relatively important question regarding transparency requirements for AI companies: At which points in time should AI companies be required to disclose information? (While I focus on transparency, this question is also applicable to other safety-relevant requirements, and is applicable to norms around voluntary actions rather than requirements.)A natural option would be to attach transparency requirements to the existing processes of pre-deployment testing and releasing a model card when

en-gb

7:25

“[Anthropic] A hacker used Claude Code to automate...

LessWrong (30+ Karma) ·

2025/08/27

Anthropic post title: Detecting and countering misuse of AI: August 2025 Read the full report here. Below lines are from the Anthropic post, and have not been edited. Accompanying images are available at the original link. We find that threat actors have adapted their operations to exploit AI's most advanced capabilities. Specifically, our report shows: Agentic AI has been weaponized. AI models are now being used to perform sophisticated cyberattacks, not just advise on how to carry them out. AI

en-gb

11:49

“AI companies have started saying safeguards are...

LessWrong (30+ Karma) ·

2025/08/27

There are two ways to show that an AI system is safe: show that it doesn't have dangerous capabilities, or show that it's safe even if it has dangerous capabilities. Until three months ago, AI companies said their models didn't have dangerous capabilities. (At the time, I wrote that the companies' eval reports didn't support their claims that their models lacked dangerous bio capabilities.) Now, Anthropic, OpenAI, Google DeepMind, and xAI say their most powerful models might have dangerous biology

en-gb

56:47

“AI Induced Psychosis: A shallow investigation” by...

LessWrong (30+ Karma) ·

2025/08/27

“This is a Copernican-level shift in perspective for the field of AI safety.” - Gemini 2.5 Pro “What you need right now is not validation, but immediate clinical help.” - Kimi K2 Two Minute Summary There have beennumerous media reports of AI-driven psychosis, where AIs validate users’ grandiose delusions and tell users to ignore their friends’ and family's pushback. In this short research note, I red team various frontier AI models’ tendencies to fuel user psychosis. I have Grok-4 role-play as

en-gb

6:07

“Do-Divergence: A Bound for Maxwell’s Demon” by...

LessWrong (30+ Karma) ·

2025/08/27

Let's start with the classic Maxwell's Demon setup. We have a container of gas, i.e. a bunch of molecules bouncing around. Down the middle of the container is a wall with a tiny door in it, which can be opened or closed by a little demon who likes to mess with thermodynamics researchers. Maxwell[1] imagined that the little demon could, in principle, open the door whenever a molecule flew toward it from the left, and close the door whenever a molecule flew toward it from the right, so that

en-gb

18:14

“Harmless reward hacks can generalize to misalignment...

LessWrong (30+ Karma) ·

2025/08/27

This post shows the abstract, introduction, and main figures from our new paper "School of Reward Hacks: Hacking harmless tasks generalizes to misaligned behavior in LLMs". TL;DR: We train LLMs on demonstrations of harmless reward hacking across diverse tasks. Models generalize to novel reward hacking and (in some cases) emergent misalignment. Authors: Mia Taylor (Center on Long-term Risk), James Chua (Truthful AI), Jan Betley (Truthful AI), Johannes Treutlein (Anthropic), and Owain Evans

en-gb

4,486 results

LessWrong (30+ Karma)

All Episodes

Similar Podcasts

Double Tap

Double Tap Productions Inc.

Primary Technology

Stephen Robles and Jason Aten

Techlandia

Technology Association of Oregon

Eye On A.I.

Craig S. Smith

The Milk Road Show

The Milk Road Show