PODCAST

LessWrong (30+ Karma)

LessWrong

Audio narrations of LessWrong posts.

technology philosophy

All Episodes

2:14

“What would a human pretending to be an AI say?” by...

LessWrong (30+ Karma) ·

2025/08/09

It always feels wrong when people post chats where they ask an LLM questions about its internal experiences, how it works, or why it did something, but I had trouble articulating why beyond a vague, "How could they possibly know that?"[1]. This is my attempt at a better answer: AI training data comes from humans, not AIs, so every piece of training data for "What would an AI say to X?" is from a human pretending to be an AI. The training data does not contain AIs describing their inner experiences

en-gb

10:44

“How anticipatory cover-ups go wrong” by Kaj_Sotala

LessWrong (30+ Karma) ·

2025/08/08

1. Back when COVID vaccines were still a recent thing, I witnessed a debate that looked like something like the following was happening: Some official institution had collected information about the efficacy and reported side-effects of COVID vaccines. They felt that, correctly interpreted, this information was compatible with vaccines being broadly safe, but that someone with an anti-vaccine bias might misunderstand these statistics and misrepresent them as saying that the vaccines were

en-gb

48:29

“METR’s Evaluation of GPT-5” by GradientDissenter

LessWrong (30+ Karma) ·

2025/08/07

METR (where I work, though I'm cross-posting in a personal capacity) evaluated GPT-5 before it was externally deployed. We performed a much more comprehensive safety analysis than we ever have before; it feels like pre-deployment evals are getting more mature. This is the first time METR has produced something we've felt comfortable calling an "evaluation" instead of a "preliminary evaluation". It's much more thorough and comprehensive than the things we've created before and it explores three

en-gb

7:58

“Civil Service: a Victim or a Villain?” by Martin...

LessWrong (30+ Karma) ·

2025/08/07

Dominic Cummings and Jennifer Pahlka are both unhappy about the civil service. However, they have different understandings of what the problem is and how it should be solved. Dominic is a politician. The problem, as he sees it, is that the civil service is disconnected from the electoral political system. Bureaucrats are appointed rather that elected, often in complex and opaque ways, and cannot even be fired by the elected politicians. This creates an self-standing, unaccountable ruling class, the

en-gb

10:35

“It’s Owl in the Numbers: Token Entanglement in...

LessWrong (30+ Karma) ·

2025/08/07

By Amir Zur (Stanford), Alex Loftus (Northeastern), Hadas Orgad (Technion), Zhuofan Josh Ying (Columbia, CBAI), Kerem Sahin (Northeastern), and David Bau (Northeastern) Links: Interactive Demo | Code | Website Summary We investigate subliminal learning, where a language model fine-tuned on seemingly meaningless data from a teacher model acquires the teacher's hidden behaviors. For instance, when a model that "likes owls" generates sequences of numbers, a model fine-tuned on these sequences also

en-gb

20:13

“No, Rationalism Is Not a Cult” by Liam Robins

LessWrong (30+ Karma) ·

2025/08/07

(I realize I'm preaching to the choir by posting this here. But I figure it's good to post it regardless.) Introduction Recently, Scott Alexander gave a list of tight-knit communities with strong values: The Amish: They live apart in tight-knit communities with strong countercultural values, and carefully control their technological and ideological environment. 10/10. Cults and communes: Any cult mature enough to have its own compound, or any communal living project, has succeeded almost as

en-gb

25:46

“Interview with Kelsey Piper on Self-Censorship and...

LessWrong (30+ Karma) ·

2025/08/07

On 17 July 2025, I sat down with Kelsey Piper to chat about politics and social epistemology. You can listen to the audio file, or read the transcript below, which has been edited for clarity. Post-Election Candor and the Costs of Silencing ZMD: Hi, I'm Zack M. Davis, here today with journalist Kelsey Piper to talk about how political pressures shape our speech and therefore our world-models: what gets said, what gets left unsaid, and how that changes over time. In particular, we had an election

en-gb

12:03

“Claude, GPT, and Gemini All Struggle to Evade...

LessWrong (30+ Karma) ·

2025/08/07

This work was done while at METR. Introduction GDM recently released a paper (Emmons et al.) showing that, contrary to previous results, the chain-of-thought (CoT) of language models can be more faithful when the model's thoughts are necessary for it to complete a task. They examine three settings where an actor model attempts to fool monitors on various tasks. In Section 5 of the paper, an actor model is tasked with solving a difficult GPQA problem within one of the subject areas

en-gb

9:01

“Re: Recent Anthropic Safety Research” by Eliezer...

LessWrong (30+ Karma) ·

2025/08/06

A reporter asked me for my off-the-record take on recent safety research from Anthropic. After I drafted an off-the-record reply, I realized that I was actually fine with it being on the record, so: Since I never expected any of the current alignment technology to work in the limit of superintelligence, the only news to me is about when and how early dangers begin to materialize. Even taking Anthropic's results completely at face value would change not at all my own sense of how dangerous machine

en-gb

4:17

“Inscrutability was always inevitable, right?” by...

LessWrong (30+ Karma) ·

2025/08/06

Here's a 2022 Eliezer Yudkowsky tweet:In context, “secure” means “secure against jailbreaks”. Source. H/t Cole Wyeth here. I find this confusing. Here's a question: are object-level facts about the world, like “tires are usually black”, encoded directly in the human-created AGI source code? If yes, then (1) yo be real, and (2) even if it happened, the source code would wind up with wildly unprecedented length and complexity, so much that it becomes basically inscrutable, just because it's a

en-gb

31:06

“Statistical takes for mech interp research and...

LessWrong (30+ Karma) ·

2025/08/06

I am currently a MATS 8.0 scholar studying mechanistic interpretability with Neel Nanda. I’m also a postdoc in psychology/neuroscience. My perhaps most notable paper analyzed the last 20 years of psychology research, searching for trends in what papers do and do not replicate. I have some takes on statistics.tl;dr Small p-values are nice. Unless they're suspiciously small. Statistical assumptions can be bent. Except for independence. Practical significance beats statistical significance. Although

en-gb

3:53

[Linkpost] “OpenAI Releases gpt-oss” by anaguma

LessWrong (30+ Karma) ·

2025/08/06

This is a link post. Introduction We’re releasing gpt-oss-120b and gpt-oss-20b—two state-of-the-art open-weight language models that deliver strong real-world performance at low cost. Available under the flexible Apache 2.0 license, these models outperform similarly sized open models on reasoning tasks, demonstrate strong tool use capabilities, and are optimized for efficient deployment on consumer hardware. They were trained using a mix of reinforcement learning and techniques informed by OpenAI's

en-gb

45:24

“The perils of under- vs over-sculpting AGI desires”...

LessWrong (30+ Karma) ·

2025/08/06

1. Summaryand Table of Contents1.1 Summary In the context of “brain-like AGI”, a yet-to-be-invented variation on actor-critic model-based reinforcement learning (RL), there's a ground-truth reward function (for humans: pain is bad, eating-when-hungry is good, various social drives, etc.), and there's a learning algorithm that sculpts the AGI's motivations into a more and more accurate approximation to the future reward of a possible plan. Unfortunately, this sculpting process tends to systematically

en-gb

49:33

“The Problem” by Rob Bensinger, tanagrabeast, yams,...

LessWrong (30+ Karma) ·

2025/08/05

This is a new introduction to AI as an extinction threat, previously posted to the MIRI website in February alongside a summary. It was written independently of Eliezer and Nate's forthcoming book, If Anyone Builds It, Everyone Dies, and isn't a sneak peak of the book. Since the book is long and costs money, we expect this to be a valuable resource in its own right even after the book comes out next month.[1] The stated goal of the world's leading AI companies is to build AI that is general enough

en-gb

32:42

“Concept Poisoning: Probing LLMs without probes” by...

LessWrong (30+ Karma) ·

2025/08/05

This post describes concept poisoning, a novel LLM evaluation technique we’ve been researching for the past couple months. We’ve decided to move to other things. Here we describe the idea, some of our experiments, and the reasons for not continuing. Contributors: Jan Betley, Jorio Cocola, Dylan Feng, James Chua, Anna Sztyber-Betley, Niels Warncke, Owain Evans. 1. Introduction LLMs can acquire semantically meaningless associations from their training data. This has been explored in work on

en-gb

6:50

“Narrow finetuning is different” by cloud, Stewy Slocum

LessWrong (30+ Karma) ·

2025/08/05

Epistemic status: an informal note. It is common to use finetuning on a narrow data distribution, or narrow finetuning (NFT), to study AI safety. In these experiments, a model is trained on a very specific type of data, then evaluated for broader properties, such as a capability or general disposition.Ways that narrow finetuning is different Narrow finetuning is different than the training procedures that frontier AI companies use, like pretraining on the internet, or posttraining on a diverse

en-gb

154:06

“Interview with Steven Byrnes on Brain-like AGI, Foom...

LessWrong (30+ Karma) ·

2025/08/05

Dr. @Steven Byrnes is one of the few people who both understands why alignment is hard, and is taking a serious technical shot at solving it. He's the author of these recently popular posts: Foom & Doom 1: "Brain in a box in a basement" Foom & Doom 2: Technical alignment is hard After his UC Berkeley physics PhD & Harvard postdoc, he became an AGI safety researcher at Astera. He's now deep in the neuroscience of reverse-engineering how human brains actually work, knowledge that could

en-gb

18:10

“Towards Alignment Auditing as a Numbers-Go-Up...

LessWrong (30+ Karma) ·

2025/08/04

Thanks to Rowan Wang and Buck Shlegeris for feedback on a draft. What is the job of an alignment auditing researcher? In this post, I propose the following answer: to build tools which increase auditing agent performance, as measured on a suite of standard auditing testbeds. A major challenge in alignment research is that we don’t know what we’re doing or how to tell if it's working. Contrast this with other fields of ML research, like architecture design, performance optimization, or RL

en-gb

15:33

“Alcohol is so bad for society that you should...

LessWrong (30+ Karma) ·

2025/08/04

This is a cross post written by Andy Masley, not me. I found it really interesting and wanted to see what EAs/rationalists thought of his arguments. This post was inspired by similar posts by Tyler Cowen and Fergus McCullough. My argument is that while most drinkers are unlikely to be harmed by alcohol, alcohol is drastically harming so many people that we should denormalize alcohol and avoid funding the alcohol industry, and the best way to do that is to stop drinking. This post is not meant to

en-gb

10:40

“Permanent Disempowerment is the Baseline” by...

LessWrong (30+ Karma) ·

2025/08/04

Permanent disempowerment without restrictions on quality of life achievable with relatively meager resources (and no extinction) seems to be a likely outcome for the future of humanity, if the current trajectory of frontier AI development continues and leads to AGI[1] shortly. This might happen as a result of at least a slight endorsement by AIs of humanity's welfare, in the context of costs for AIs being about matter or compute rather than technological advancements and quality of infrastructure.

en-gb

4,486 results

LessWrong (30+ Karma)

All Episodes

Similar Podcasts

Download This Show

ABC Australia

The DroneOn Show

Mike & Kevin

The Good Tech Companies

HackerNoon

TechCrunch Industry News

TechCrunch

Tech News Briefing

Tech News Briefing