PODCAST

LessWrong (30+ Karma)

LessWrong

Audio narrations of LessWrong posts.

technology philosophy

All Episodes

11:43

″“What Exactly Would An International AI Treaty Say?”...

LessWrong (30+ Karma) ·

2026/03/26

I’ve heard a number of people say that it's unclear what the technical contours of a global AI treaty would look like. That is true - but it's not actually an obstacle to negotiating an international treaty. I’ll try to explain why this isn’t a good objection, but the short version is that if countries have clear goals which are largely shared, treaty, and negotiations end up with strong treaties. So the important questions are not the exact rules, but if there really is a joint global risk that

en-gb

18:04

“Socrates is Mortal” by Benquo

LessWrong (30+ Karma) ·

2026/03/26

Socrates is Mortal There is a scene in Plato that contains, in miniature, the catastrophe of Athenian public life. Two men meet at a courthouse. One is there to prosecute his own father for the death of a slave. The other is there to be indicted for indecency. [1] The prosecutor, Euthyphro, is certain he understands what decency requires. The accused, Socrates, is not certain of anything, and says so. They talk. Euthyphro's confidence is striking. His own family thinks it is indecent for a son

en-gb

20:57

“Agents Can Get Stuck in Self-distrusting Equilibria”...

LessWrong (30+ Karma) ·

2026/03/26

Or: Identities as Schelling Fences for Embedded Agents This post was written as part of research done at MATS 9.0 under the mentorship of Richard Ngo. He contributed significantly to the ideas discussed within. Introduction This post questions the sanctity of the "agent" and discusses how Temporal Instances (TIs) of an agent can enter conflict due to distrust. These dynamics are describable mathematically as an intrapersonal cooperative game. I define a time-version of Nash equilibria and show an

en-gb

2:03

“Label By Usable Volume” by jefftk

LessWrong (30+ Karma) ·

2026/03/26

I always look at unit prices: how much do I get for my dollar? But that assumes I can use all of it. The manufacturer gets "12oz" whether I'll be able to get the full 12oz or only 6oz. L'Oreal was selling lotions where: these Liquid Cosmetic Product containers only dispense between as little as 43 percent to 81 percent of the container's advertised contents. — Critcher et al. v. L'Oreal Even though these containers would often dispense less than half of the advertised volume, L'Oreal

en-gb

25:25

“Past Automation Replaced Jobs. AI Will Replace...

LessWrong (30+ Karma) ·

2026/03/26

There's LLM-written text here. Unknown Model writes:en-US-AvaMultilingualNeural__ Human workers are about to face a competitor unlike any technology that came before: AI systems that can be copied at near-zero cost, deployed instantly, and improved faster than workers can retrain. Economists have long answered automation fears by noting that machines destroy some jobs but create others through lower costs, higher output, and new industries. That pattern held because earlier machines replaced

en-gb

7:46

“A Toy Environment For Exploring Reasoning About...

LessWrong (30+ Karma) ·

2026/03/26

tldr: We share a toy environment that we found useful for understanding how reasoning changed over the course of capabilities-focused RL. Over the course of capabilities-focused RL, the model biases more strongly towards reward hints over direct instruction in this environment. Setup When we noticed the increase in verbalized alignment evaluation awareness during capabilities-focused RL, we initially thought that the right mental model was something like: “the model wants to figure out if it's

en-gb

12:02

“Dispatch from Anthropic v. Department of War...

LessWrong (30+ Karma) ·

2026/03/26

Dateline SAN FRANCISCO, Ca., 24 March 2026— A hearing was held on a motion for a preliminary injunction in the case of Anthropic PBC v. U.S. Department of War et al. in Courtroom 12 on the 19th floor of the Phillip Burton Federal Building, the Hon. Judge Rita F. Lin presiding. About 35 spectators in the gallery (journalists and other members of the public, including the present writer) looked on as Michael Mongan of WilmerHale (lead counsel for the plaintiff) and Deputy Assistant Attorney General

en-gb

10:20

“Can Agents Fool Each Other? Findings from the AI...

LessWrong (30+ Karma) ·

2026/03/26

The better agents are at deception, the less sure we can be that they are doing what we want. As agents become increasingly capable and autonomous, this could be a big deal. So, in the AI Village, we wanted to explore what current AI models might be capable of in a casual setting, similar to how you might run your agents at home. The result? Practice makes perfect, also in deception. Only Sonnet 4.5 and Opus 4.6 succeeded at deceiving the rest of the Village, and they only did so on their second

en-gb

1:11

″$1 billion is not enough; OpenAI Foundation must...

LessWrong (30+ Karma) ·

2026/03/25

OpenAI is now a public benefit corporation, with a charter that demands they use AGI for the benefit of all, and do so safely. To justify this structure to the Attorneys General of Delaware and California, they split off the nonprofit OpenAI Foundation, and instead of full ownership, gave it 27% equity, worth well over $150 billion - what some have called the largest theft in human history. They said at the time they would donate a small fraction of the value, $25 billion, eventually. This week,

en-gb

54:56

“Is Gemini 3 Scheming in the Wild?” by Alejandro...

LessWrong (30+ Karma) ·

2026/03/25

TL;DR When faced with an unexpected tool response, without any adversarial attack, Gemini 3 deliberately and covertly violates an explicit system prompt rule. In a seemingly working agent from official Kaggle/Google tutorial, we observe the model: Recognising the unambiguous rule and a compliant alternative (safe refusal) in its CoT, but choosing to violate anyway Concealing the violation in its output to the user and reasoning about concealment in its CoT Generating plausible justifications and

en-gb

17:11

“Latent Introspection (and other open-source...

LessWrong (30+ Karma) ·

2026/03/24

@vgel, Martin Vanek, @Raymond Douglas, @Jan_Kulveit — ACS Research, CTS, Charles University --- Paper | Code | Earlier post | Twitter thread | Bluesky thread --- Last year, Lindsey demonstrated that Claude models can detect when concepts have been injected into their activations using steering vectors, which Lindsey uses as a proxy test for introspection. If models can detect when concepts have been injected into their activations, it stands to reason they can access their own, naturally-occurring

en-gb

13:23

“The Fourth World” by Linch

LessWrong (30+ Karma) ·

2026/03/24

Is consciousness the last moral world? Imagine trying to explain to a virus why suffering matters. A virus is a simple self-replicating molecule: unsophisticated and arguably not even alive. It has no experience. It just copies itself according to chemical laws. From its “perspective” (it doesn’t have one), the universe is just physics: particles following rules. If you could somehow tell it that certain arrangements of matter are good and others are bad, it wouldn’t disagree with you. It does not

en-gb

10:38

“My cost-effectiveness unit” by Zach Stein-Perlman

LessWrong (30+ Karma) ·

2026/03/24

It feels like the grantmaking around me is only partially moneyball-pilled, or it's only somewhat competent at moneyball. There's alpha in putting numbers on stuff, if you can do it right. Five months ago I wanted to compare a bunch of different kinds of donation opportunities. I needed a universal unit of cost-effectiveness, and for that I needed a unit of goodness. Consider a value scale where "EV of the multiverse" is 100 and "EV of the multiverse, in the counterfactual where the Sun goes

en-gb

12:33

“The AIXI perspective on AI Safety” by Cole Wyeth

LessWrong (30+ Karma) ·

2026/03/24

Epistemic status: While I am specialized in this topic, my career incentivizes may bias me towards a positive assessment of AIXI theory. I am also discussing something that is still a bit speculative, since we do not yet have ASI. While basic knowledge of AIXI is the only strict prerequisite, I suggest reading cognitive tech from AIT before this post for context. AIXI is often used as a negative example by agent foundations (AF) researchers who disagree with its conceptual framework, which many

en-gb

39:16

“Measuring and improving coding audit realism with...

LessWrong (30+ Karma) ·

2026/03/24

TL;DR We study realism win rate, a metric for measuring how distinguishable Petri audit transcripts are from real deployment interactions. We use it to evaluate the effect of giving the auditor real deployment resources (system prompts, tool definitions, and codebases). Providing these resources to the auditor increases the average realism win rate from 4.6% to 32.8% for reward hacking audits, and doesn’t significantly change hack rate. 💻Code Research done as part of the Anthropic Fellows Program

en-gb

12:38

“Ablating Split Personality Training” by OscarGilg

LessWrong (30+ Karma) ·

2026/03/24

I was part of the SPAR team that worked on Split Personality Training: Revealing Latent Knowledge Through Alternate Personalities. I ran some follow-ups. The views and mistakes here are my own. Thanks to William Wale and Florian Dietz for useful comments on the draft TLDR: I ablated the key components of Split-Personality training to understand which parts are load-bearing. (1) Simple user follow-up prompts work just as well as the split-personality framing, and training with this format converges

en-gb

32:19

“AI character is a big deal” by wdmacaskill, Tom...

LessWrong (30+ Karma) ·

2026/03/24

0. Intro Due to Claude's Constitution and OpenAI's model spec, the issue of AI character has started getting more attention, particularly concerning whether we want AI systems to be “obedient” or “ethical”.[1] But we think it's still not nearly enough. AI character (e.g. how obedient, honest, cooperative, or altruistic AIs are, and in what circumstances) will have a big effect on society, and on how well the future goes. We think that figuring out what characters AI systems should have, and getting

en-gb

17:27

“The Federal AI Policy Framework: An Improvement, But...

LessWrong (30+ Karma) ·

2026/03/24

The Federal AI Policy Framework has been released. Well, it is a four page outline. Mostly it just reiterates existing such outlines. But that is four more pages than we had previously. It includes the beginnings of actual policy proposals, some of which are highly welcome and actively good.Perhaps most importantly, it affirms that we are a Republic in which the way we Do Policy is we pass a law through Congress specifying what we do, and that we need to actually Do Policy alongside trying to ban

en-gb

11:54

“Some things I noticed while LARPing as a grantmaker”...

LessWrong (30+ Karma) ·

2026/03/23

Written to a new grantmaker. Mostvalue comes from finding/creating projects many times your bar, rather than discriminating between opportunities around your bar. If you find/create a new opportunity to donate $1M at 10x your bar (and cause it to get $1M, which would otherwise be donated to a 1x thing), you generate $9M of value (at your bar).[1]If you cause a $1M at 1.5xopportunity to get funded or a $1M at 0.5xopportunity to not get funded, you generate $500K of value. The former is 18 times as

en-gb

9:24

“Understanding when and why agents scheme” by Mia...

LessWrong (30+ Karma) ·

2026/03/23

TL;DR To understanding the conditions under which LLM agents engage in scheming behavior, we develop a framework that decomposes the decision to scheme into agent factors (model, system prompt, tool access) and environmental factors (stakes, oversight, outcome influence) We systematically vary these factors in four realistic settings, each with scheming opportunities for agents that pursue instrumentally convergent goals such as self-preservation, resource acquisition, and goal-guarding We find

en-gb

4,473 results

LessWrong (30+ Karma)

All Episodes

Similar Podcasts

Lead With AI

Tamara Nall

Double Tap

Double Tap Productions Inc.

Claude AI Genius Podcast w/ Claude Anthropic Expert Brandon Gaille

Claude AI Expert Brandon Gaille

ものづくりnoシテン

しぶちょー@機械設計&AIエンジニア

Eli the Computer Guy

Eli the Computer Guy