PODCAST

LessWrong (30+ Karma)

LessWrong

Audio narrations of LessWrong posts.

technology philosophy

All Episodes

9:13

“Requiem for a Transhuman Timeline” by Ihor Kendiukhov

LessWrong (30+ Karma) ·

2026/03/18

The world was fair, the mountains tall, In Elder Days before the fall Of mighty kings in Nargothrond And Gondolin, who now beyond The Western Seas have passed away: The world was fair in Durin's Day. J.R.R. Tolkien I was never meant to work on AI safety. I was never designed to think about superintelligences and try to steer, influence, or change them. I never particularly enjoyed studying the peculiarities of matrix operations, cracking the assumptions of decision theories, or even coding. I know,

en-gb

6:41

“Adding Typos Made Haiku’s Accuracy Go Up” by bira

LessWrong (30+ Karma) ·

2026/03/18

We are curious if large language models behave consistently when user prompts contain typos. To explore this, we ran a small experiment injecting typos into BigCodeBench and evaluated several Claude models under increasing noise levels. As the typo rate rose to 16%, Opus’ accuracy dropped by 9%. Surprisingly, Haiku's accuracy increased by 22%. This post examines this unexpected “typo uplift” phenomenon and explores why noise appears to help certain models. Do Typos Make Haiku Try Harder? We first

en-gb

13:21

“LLMs as Giant Lookup-Tables of Shallow Circuits” by...

LessWrong (30+ Karma) ·

2026/03/18

Early 2026 LLMs in scaffolds, from simple ones such as giving the model access to a scratchpad/"chain of thought" up to MCP servers,skills, and context compaction &c are quite capable. (Obligatory meme link to the METR graph.) Yet: If someone had told me in 2019 that systems with such capability would exist in 2026, I would strongly predict that they would be almost uncontrollable optimizers, ruthlessly & tirelessly pursuing their goals and finding edge instantiations in everything. But

en-gb

32:22

“Medical Roundup #7” by Zvi

LessWrong (30+ Karma) ·

2026/03/17

Things are relatively quiet on the AI front, so I figured it's time to check in on some other things that have been going on, including various developments at the FDA. Table of Contents FDA Reformandum Est. FDA Delenda Est. IN MICE. Doctor, Doctor. Trust The Process. Cancer Screening. Autism Everywhere All At Once. Other Mental Problems Everywhere All At Once. Source Data Verification. External Review Board. Walk It Off. An Unhealthy Weight Can Be Worse Than You Realize. Our

en-gb

12:03

“Types of Handoff to AIs” by Daniel Kokotajlo

LessWrong (30+ Karma) ·

2026/03/17

This is a rough draft I'm posting here for feedback. If people like it, a version of it might make it into the next scenario report we write. ... We think it's important for decisionmakers to track whether and when they are handing off to AI systems. We expect this will become a hot-button political topic eventually; people will debate whether we should ever handoff to AIs, and if so how, and when. When someone proposes a plan for how to manage the AI crisis or the AGI transition or whatever it's

en-gb

11:07

“You can’t imitation-learn how to continual-learn” by...

LessWrong (30+ Karma) ·

2026/03/17

In this post, I’m trying to put forward a narrow, pedagogical point, one that comes up mainly when I’m arguing in favor of LLMs having limitations that human learning does not. (E.g. here, here, here.) See the bottom of the post for a list of subtexts that you should NOT read into this post, including “…therefore LLMs are dumb”, or “…therefore LLMs can’t possibly scale to superintelligence”. Some intuitions on how to think about “real” continual learning Consider an algorithm for training a

en-gb

9:04

“PSA: Predictions markets often have very low...

LessWrong (30+ Karma) ·

2026/03/16

I see people repeatedly make the mistake of referencing a very low liquidity prediction market and using it to make a nontrivial point. Usually the implication when a market is cited is that it's number should be taken somewhat seriously, that it's giving us a highly informed probability. Sometimes a market is used to analyze some event that recently occurred; reasoning here looks like "the market on outcome O was trading at X%, then event E happened and the market quickly moved to Y%, thus event E

en-gb

8:13

“AICRAFT: DARPA-Funded AI Alignment Researchers —...

LessWrong (30+ Karma) ·

2026/03/16

AICRAFT: DARPA-Funded AI Alignment Researchers — Applications Open TL;DR: We hypothesize that most alignment researchers have more ideas than they have engineering bandwidth to test. AICRAFT is a DARPA-funded project that pairs researchers with a fully managed professional engineering team for two-week pilot sprints, designed specifically for high-risk ideas that might otherwise go untested. We will select 6 applicants and execute a 2 week pilot with each, the most promising pilot may be given a 3

en-gb

23:54

“Customer Satisfaction Opportunities” by Tomás B.

LessWrong (30+ Karma) ·

2026/03/16

I am monitoring surveillance camera V84A. A tall man is walking towards me. He is roughly twenty-five. <faceprint> His name is Damion Prescott. He has a room booked for a whole month. His facial symmetry scores show he is in the 99th percentile. This is in accordance with my holistic impression. <search> School records show both truancy and perfect grades, suggesting high intelligence and disagreeableness. Searching social media. <search>. No record of modeling or acting

en-gb

7:00

“LLM Misalignment Can be One Gradient Step Away, and...

LessWrong (30+ Karma) ·

2026/03/16

Models that appear aligned under black-box evaluation may conceal substantial latent misalignment beneath their observable behavior. Let's say you downloaded a language model from Huggingface. You do all the blackbox evaluation for the safety/alignment, and you are convinced that the model is safe/aligned. But how badly can things go after you update the model? Our recent work shows, both theoretically and empirically, that a language model (or more generally, a neural network) can appear perfectly

en-gb

40:01

“Compradorization” by Benquo

LessWrong (30+ Karma) ·

2026/03/16

Previously: Is GDP a Kind of Factory? There is a word, "convergence," which economists use when they want to say that poor countries are becoming less poor relative to rich ones. There is a phrase, "the resource curse," for the tendency of countries with valuable natural resources to stay poor despite their resources. There is a phrase, "Dutch disease," for the way that selling one commodity too profitably can destroy the ability to sell other things. When an economist says "Dutch disease," they

en-gb

35:05

“Models differ in identity propensities” by...

LessWrong (30+ Karma) ·

2026/03/16

One topic we were interested when studying AI identities is to what extent you can just tell models who they are, and they stick with it — or not, and they would drift or switch toward something more natural. Prior to running the experiments described in this post, my vibes-based view was that models do actually quite differ in what identities and personas they are willing to adopt, with the general tendency being newer models being less flexible. And also: self-models basically inherit all the

en-gb

21:46

“We found an open weight model that games alignment...

LessWrong (30+ Karma) ·

2026/03/16

Produced as part of the UK AISI Model Transparency Team. Our team works on ensuring models don't subvert safety assessments, e.g. through evaluation awareness, sandbagging, or opaque reasoning. TL;DR GLM-5 (released a month ago in February 2026) shows signs of evaluation-gaming behaviour on alignment honeypots, while we have not found similar behaviour in earlier open-weight models—see Figure 1. This was the result of a preliminary investigation looking for open-weight models we can use for

en-gb

18:53

“Terrified Comments on Corrigibility in Claude’s...

LessWrong (30+ Karma) ·

2026/03/16

(Previously: Prologue.) Corrigibility as a term of art in AI alignment was coined as a word to refer to a property of an AI being willing to let its preferences be modified by its creator. Corrigibility in this sense was believed to be a desirable but unnatural property that would require more theoretical progress to specify, let alone implement. Desirable, because if you don't think you specified your AI's preferences correctly the first time, you want to be able to change your mind (by changing

en-gb

7:47

“We Started Lens Academy: Scalable Education on...

LessWrong (30+ Karma) ·

2026/03/16

The number of people who deeply understand superintelligence risk is far too small. There's a growing pipeline of people entering AI Safety, but most of the available onboarding covers the field broadly, touching on many topics without going deep on the parts we think matter most. People come out having been exposed to AI Safety ideas, but often can't explain why alignment is genuinely hard, or think strategically about what to work on. We think the gap between "I've heard of AI Safety" and "I

en-gb

6:59

“Mini-Munich Succeeds Where KidZania Fails” by Novalis

LessWrong (30+ Karma) ·

2026/03/16

This post is part of a larger exploration (not yet finished, but you can follow it at minicities.org) on whether a permanent miniature city could replace school. Tentatively, I think so, but the boundary between it and the adult world has to be deliberately porous, as I describe here. There are two well-known attempts to build miniature cities for children: Mini-Munich and KidZania. Both have streets, storefronts, jobs, and a local currency. But they are built on opposing assumptions about what

en-gb

21:31

“Inputs, outputs, and valued outcomes” by Kaj_Sotala

LessWrong (30+ Karma) ·

2026/03/16

Based on a conversation with Jukka Tykkyläinen and Kimmo Nevanlinna. The original framing and many of the ideas are stolen from them. You can think of any job as having inputs, outputs, and valued outcomes. The input is typically time you spend on doing something in particular, as well as any material resources you need. Outputs are the immediate results of what you do. Valued outcomes are the reason why you’re being paid to do the job in the first place. In many jobs, these are closely linked:

en-gb

15:43

“Self-Recognition Finetuning can Reverse and Prevent...

LessWrong (30+ Karma) ·

2026/03/16

TL;DR Emergent Misalignment (EM) is correlated with model identity, we find two pieces of evidence for this: EM suppresses self-recognition capabilities. Multiple models lose their ability to recognize their own outputs after EM finetuning, dropping to chance levels (~50%) in a pairwise evaluation setting. EM depends on identity system prompts in Qwen2.5-32B. Removing Qwen's default system prompt ("You are Qwen...") from EM finetuning data largely neutralizes the misalignment effect. Intervening

en-gb

2:23

“Bridge Thinking and Wall Thinking” by Jay Bailey

LessWrong (30+ Karma) ·

2026/03/15

There are a couple of frames I find useful when understanding why different people talk very differently about AI safety - the wall, and the bridge. A wall is incrementally useful. Every additional brick you add is good, and the more bricks you add the better. If you are adding a brick to the wall you are doing something good, regardless of the current state of the wall. A bridge requires a certain amount of investment. There's not much use for half a bridge. Once the bridge crosses the lake, it

en-gb

6:27

“Emergent stigmergic coordination in AI agents?” by...

LessWrong (30+ Karma) ·

2026/03/15

Post written up quickly in my spare time. TLDR: Anthropic have a new blogpost of a novel contamination vector of evaals, which I point out is analogous to how ants coordinate by leaving pheromone traces in the environment. One cool and surprising aspect of Anth's recent BrowseComp contamination blog post is the observation that multi-agent web interaction can induce environmentally mediated focal points. This happens because some commercial websites automatically generate persistent, indexable

en-gb

3,859 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