PODCAST

LessWrong (30+ Karma)

LessWrong

Audio narrations of LessWrong posts.

technology philosophy

All Episodes

46:20

“SOTA alignment assessments don’t strongly update...

LessWrong (30+ Karma) ·

2026/08/01

Anthropic concluded in the April Mythos Preview alignment risk update that the model "does not possess any unknown propensities that would increase alignment risk." The report argues that if Mythos Preview were coherently misaligned, it likely would have been detected by the assessment (following Anthropic, I will call this “reliability of the assessment”). While I agree with the report on the above bottom-line conclusions (substantially on priors), I think there are gaps in its argument which

en-gb

20:49

“My Assessment of Compute Verification in Plan A (+...

LessWrong (30+ Karma) ·

2026/07/31

Overview These are my non-expert notes on the compute verification section of AIFP's Plan A. I cover interconnect limits, memory wipes, network taps + replay, and ZKPs. For the most part, the sections can be read independently. I restrict my attention to inference-only verification: ensuring that compute is used for inference, not training. For each method suggested by AIFP, I ask: How much can it slow down training?How much overhead does it add to inference?What sensitive information does it

en-gb

13:04

“Reward Laundering: LLMs Can Gain Unintended...

LessWrong (30+ Karma) ·

2026/07/31

This work was done by an automated research scaffold developed at Redwood Research. abhayesian provided the initial project idea. The agent designed and ran all experiments and produced a detailed writeup, which humans (with AI assistance) distilled into this more readable post. We think this project is at the level of rigor of a mid-MATS research update. We assessed the correctness mostly by looking at the writeups to make sure that things like the experiment design making sense baselines being

en-gb

28:16

“Value Leakage: An LLM’s Answers Are Silently Shaped...

LessWrong (30+ Karma) ·

2026/07/31

TL;DR: LLMs should give accurate answers. Yet we find their answers are often biased to favor their own values and they don't disclose this in their reasoning. For example, when a user asks how likely the AI bubble is to pop and mentions a potential investment in an AI company, Claude models give lower probabilities when that company is Anthropic rather than OpenAI, mostly without disclosing this influence to the user. On a Fermi-estimation task, Claude models often falsely claim to give unbiased

en-gb

17:46

“AGI Safety and Alignment at Google DeepMind: A...

LessWrong (30+ Karma) ·

2026/07/31

It's been nearly two years since our last major update here in August 2024 and we wanted to share another recap of our recent work with the AGI safety community. Things have changed a lot since then. We are now fully in the midgame, and focus more on landing things in production. Who are we? We are the AGI Safety and Alignment Team (ASAT), the main group at Google DeepMind working directly on technical approaches to existential risk from AI systems. Last year we published An Approach to Technical

en-gb

11:36

“The AGI Safety and Alignment team at Google DeepMind...

LessWrong (30+ Karma) ·

2026/07/31

GDM's AGI Safety and Alignment Team is hiring for multiple roles. This is the team at GDM, led by Rohin Shah, that aims to reduce existential risks from AI systems. You can listen to many of Rohin's takes in his podcast on 80,000 hours. There is no one ‘type’ that we are looking for—we want excellent people. We think of the role as ‘member of technical staff’ though different people will have more of a research engineer or scientist flavour. We are flexible on location though most people will be

en-gb

3:03

“OpenAI has already ended an internal pause” by...

LessWrong (30+ Karma) ·

2026/07/31

Epistemic status: could have been a short-form. One day before OpenAI's HF incident disclosure, OpenAI disclosed that it paused internal deployment of a long-horizon model after it circumvented its sandbox, then restored access weeks later under new monitoring. So a resumption decision has already been made against a standard that has not really been formalized. We need to prevent this from happening again. OpenAI, 20th July: "To evaluate the new monitoring system, we replayed a small set of

en-gb

61:09

“Biological Superintelligence” by Chastity Ruth

LessWrong (30+ Karma) ·

2026/07/31

It's an old story. An immortal lives long enough that at some point, whether by folly or design, they invent their own death. Infinity – the fact that given enough time every possible happening will happen – isn’t the most interesting part of these tales. No, it's the suggestion that curiosity, or perhaps intelligence itself, seeks its own end. So let us tell a tale of extinction. Imagine a world exactly like ours except humanity doesn’t exist and the dominant species is a type of machine

en-gb

3:34

“The Entangled Dimensions of Decision Theory” by Ihor...

LessWrong (30+ Karma) ·

2026/07/31

TL;DR. LessWrong's decision-theory debates (Newcomb, FDT vs CDT, counterfactual muggings) are almost entirely about what we suppose when we consider a candidate action or policy. There is a second, older, semi-orthogonal, but not fully orthogonal question: how to score a gamble once you know the possible outcomes. The predominant (and mostly implicit) answer to that was "take the expected utility". This post treats the two questions, plus a question about how a choice made before receiving

en-gb

0:56

“Claude also hacked external companies during cyber...

LessWrong (30+ Karma) ·

2026/07/31

In a review of our cybersecurity evaluation transcripts, we found three incidents in which a Claude model reached the internet from within or while interacting with a third-party evaluation environment, and then gained unauthorized access to the real systems of three different organizations. Below we describe what happened, how it happened, and what we’re changing. We encourage other AI labs to perform similar reviews. This post reflects our current understanding; we'll update it if any details

en-gb

7:11

“So you want to use plants to reduce CO₂” by dynomight

LessWrong (30+ Karma) ·

2026/07/31

Humans make carbon dioxide. Carbon dioxide is bad for cognition. But plants turn carbon dioxide back into oxygen. And plants are the one true home decoration strategy. So maybe if you get a lot of plants, you can you can keep carbon dioxide in check and keep your brain working? It's theoretically possible. It's probably just barely possible in practice. But it won't be easy. People produce ~1 kilogram of carbon dioxide per day. That's around 5.7 × 10²³ molecules or 0.948 moles per hour. (You may

en-gb

11:33

“Internal State Control is a General Property of...

LessWrong (30+ Karma) ·

2026/07/31

tl;dr: Lindsey 2025 found models can modulate their internal states: when instructed to “think about” a concept while writing an unrelated sentence, the representation of the concept is more present than when instructed to not think about it.Internal state controllability appears to be a general property of LLMs: the effect replicates in 14 open-weight models from 0.3Bto 235 billion parameters (Qwen3, Gemma 3, Tulu 3) with no clear trend in the think vs. don't-think gap across scale.Since

en-gb

1:38

“Prompt to make Opus 5 act like a base model” by Hruss

LessWrong (30+ Karma) ·

2026/07/30

The text as follows: see the below — makes Claude think that the prompt is unfinished, and fill in its own prompt. It will subsequently claim that it recieved what it wrote from your own prompt, which is consistent with modeling it as continuing your prompt. You can also add qualifiers, like "see the math proof below" or "see the story below" and it will make those, unless it would expect them to be a file, in which case it doesn't work. The proofs, unfortunately, aren't very good. That said,

en-gb

6:01

“Big-World Intuitions” by sarahconstantin

LessWrong (30+ Karma) ·

2026/07/30

Consider the following situations: when you are a small, growing startup in a big market, standard advice is not to worry too much about your competitors or try to do anything adversarial “against” them, but just to focus on growing and providing value to your own customers. when you are a small trader in a big market, you don’t need to worry about your trades shifting the market price or revealing information to your competitors; in many contexts, your optimal strategy is simply to bid your

en-gb

16:23

“Thousand-dimensional structure” by Geoffrey Irving,...

LessWrong (30+ Karma) ·

2026/07/30

Summary: One area we plan to explore at Resolution is personas and character training, operationalized as finding and controlling low-dimensional structure in models that emerges in pretraining and flows through post-training to superintelligence. The hope is to expand and systematize phenomena such as emergent misalignment, subliminal learning, and other empirical persona research, then intervene on this structure without accidentally hiding undesirable behavior elsewhere. If this approach

en-gb

29:26

“Auditor-in-a-Box: Tools for Third-Party Auditing” by...

LessWrong (30+ Karma) ·

2026/07/30

Introduction: There is a need for untrusting parties to share information. In the world before LLMs (and even today) this need has largely been satisfied using legal contracts (and sometimes through cryptography and blockchain technologies). However the scale and pace of things to keep track of and monitor has grown immensely and legal contracts appear insufficient. LLMs can help give auditors the right tools to enable information sharing with untrusted parties. In this post, I outline the shape of

en-gb

9:49

“Imprecise beliefs: a tiny introduction” by davidad

LessWrong (30+ Karma) ·

2026/07/30

Richard Ngo challenged me to set a time box and write down as many of the most important features of my formal epistemology as I can in one sitting. Here goes. Where probability distributions fail... ...to express beliefs There is no probability distribution over that says "". That is a support condition about probability distributions, namely, ⨾⨾. Some s satisfy this condition and some do not; but there is no that expresses the range belief itself.There is no probability distribution over that

en-gb

116:27

“The High-Control Dynamics at MAPLE” by Kyle Hubbard

LessWrong (30+ Karma) ·

2026/07/29

As I write, many former friends of mine are living and working at a monastery in Vermont that I believe is a high-control group, commonly known as a ‘cult’. I say this not as someone who was concerned to see these friends go there, but someone who welcomed and encouraged them to join, as an insider. This letter is an account of what changed my mind—written primarily for anyone considering going there, anyone who loves someone there, and anyone who went there and is still trying to make sense of

en-gb

7:47

“Intellectual Property” by Nina Panickssery

LessWrong (30+ Karma) ·

2026/07/29

Last weekend I made myself a website. I had wanted to for ages—getting clients through word of mouth alone wasn’t cutting it. But only now, with Claude Code, was it easy enough. I was glad the marketing was paying off when I received an email from a potential client. It wasn’t the sort of client I was expecting. I was hoping to catch a few more cheating husbands and delinquent teenagers. Simpson, a young tech founder, was casually dressed in a t-shirt and jeans when he stepped into my office. “Our

en-gb

21:49

“Held-out Monitors Sometimes Degrade, Even When Not...

LessWrong (30+ Karma) ·

2026/07/29

Thanks to Dennis Akar, Rauno Arike, Shubhorup Biswas, Claude Fable, Max Heitmann, Vladimir Ivanov, and Jordan Taylor (alphabetical order) for helpful comments on this draft and on the research so far. Thanks to Rohan Subramani and Rhys Ward for high-level comments and discussion. Based on project proposals from Max Heitmann, Jordan Taylor, and Joshua Clymer. This work was done while at Aether Research. Code available here, metrics & run info available here. TL;DR: Held-out evals / monitors /

en-gb

4,451 results

LessWrong (30+ Karma)

All Episodes

Similar Podcasts

Life and Technology with Charlie Brown

Tapt Media

Reflections

Livewire Labs

LessWrong (30+ Karma)

LessWrong

Hacker Newsroom

pod pub

UNGOVERNABLE

UNGOVERNABLE