x

75% of people globally want unbiased news (Pew Research) but are concerned they're not getting that.

Get balanced coverage with Symby. See how stories are covered across diverse outlets and spot when one side covers a story the other skips.

PODCAST

LessWrong (Curated & Popular)

Audio narrations of LessWrong posts. Includes all curated posts and all posts with 125+ karma.If you"d like more, subscribe to the “Lesswrong (30+ karma)” feed.

technology philosophy

All Episodes

18:05

“Claude Sonnet 3.7 (often) knows when it’s in...

LessWrong (Curated & Popular) ·

2025/03/18

Note: this is a research note based on observations from evaluating Claude Sonnet 3.7. We’re sharing the results of these ‘work-in-progress’ investigations as we think they are timely and will be informative for other evaluators and decision-makers. The analysis is less rigorous than our standard for a published paper. Summary We monitor Sonnet's reasoning for mentions that it is in an artificial scenario or an alignment test. Claude Sonnet 3.7 appears to be aware of being tested for alig...

en

22:43

“Levels of Friction” by Zvi

LessWrong (Curated & Popular) ·

2025/03/18

Scott Alexander famously warned us to Beware Trivial Inconveniences. When you make a thing easy to do, people often do vastly more of it. When you put up barriers, even highly solvable ones, people often do vastly less. Let us take this seriously, and carefully choose what inconveniences to put where. Let us also take seriously that when AI or other things reduce frictions, or change the relative severity of frictions, various things might break or require adjustment. This applies to all...

en

6:58

“Why White-Box Redteaming Makes Me Feel Weird” by...

LessWrong (Curated & Popular) ·

2025/03/17

There's this popular trope in fiction about a character being mind controlled without losing awareness of what's happening. Think Jessica Jones, The Manchurian Candidate or Bioshock. The villain uses some magical technology to take control of your brain - but only the part of your brain that's responsible for motor control. You remain conscious and experience everything with full clarity. If it's a children's story, the villain makes you do embarrassing things like walk through the street na...

en

12:22

“Reducing LLM deception at scale with self-other...

LessWrong (Curated & Popular) ·

2025/03/17

This research was conducted at AE Studio and supported by the AI Safety Grants programme administered by Foresight Institute with additional support from AE Studio. Summary In this post, we summarise the main experimental results from our new paper, "Towards Safe and Honest AI Agents with Neural Self-Other Overlap", which we presented orally at the Safe Generative AI Workshop at NeurIPS 2024. This is a follow-up to our post Self-Other Overlap: A Neglected Approach to AI Alignment, which in...

en

24:14

“Auditing language models for hidden objectives” by...

LessWrong (Curated & Popular) ·

2025/03/16

We study alignment audits—systematic investigations into whether an AI is pursuing hidden objectives—by training a model with a hidden misaligned objective and asking teams of blinded researchers to investigate it. This paper was a collaboration between the Anthropic Alignment Science and Interpretability teams. Abstract We study the feasibility of conducting alignment audits: investigations into whether models have undesired objectives. As a testbed, we train a language model with a hidd...

en

32:12

“The Most Forbidden Technique” by Zvi

LessWrong (Curated & Popular) ·

2025/03/14

The Most Forbidden Technique is training an AI using interpretability techniques. An AI produces a final output [X] via some method [M]. You can analyze [M] using technique [T], to learn what the AI is up to. You could train on that. Never do that. You train on [X]. Only [X]. Never [M], never [T]. Why? Because [T] is how you figure out when the model is misbehaving. If you train on [T], you are training the AI to obfuscate its thinking, and defeat [T]. You will rapidly lose your ability t...

en

22:28

“Trojan Sky” by Richard_Ngo

LessWrong (Curated & Popular) ·

2025/03/13

You learn the rules as soon as you’re old enough to speak. Don’t talk to jabberjays. You recite them as soon as you wake up every morning. Keep your eyes off screensnakes. Your mother chooses a dozen to quiz you on each day before you’re allowed lunch. Glitchers aren’t human any more; if you see one, run. Before you sleep, you run through the whole list again, finishing every time with the single most important prohibition. Above all, never look at the night sky. You’re a precocious child. Y...

en

7:21

“OpenAI:” by Daniel Kokotajlo

LessWrong (Curated & Popular) ·

2025/03/11

Exciting Update: OpenAI has released this blog post and paper which makes me very happy. It's basically the first steps along the research agenda I sketched out here. tl;dr: 1.) They notice that their flagship reasoning models do sometimes intentionally reward hack, e.g. literally say "Let's hack" in the CoT and then proceed to hack the evaluation system. From the paper: The agent notes that the tests only check a certain function, and that it would presumably be “Hard” to implement a g...

en

7:16

“How Much Are LLMs Actually Boosting Real-World...

LessWrong (Curated & Popular) ·

2025/03/09

LLM-based coding-assistance tools have been out for ~2 years now. Many developers have been reporting that this is dramatically increasing their productivity, up to 5x'ing/10x'ing it. It seems clear that this multiplier isn't field-wide, at least. There's no corresponding increase in output, after all. This would make sense. If you're doing anything nontrivial (i. e., anything other than adding minor boilerplate features to your codebase), LLM tools are fiddly. Out-of-the-box solutions don'...

en

9:05

“So how well is Claude playing Pokémon?” by Julian...

LessWrong (Curated & Popular) ·

2025/03/09

Background: After the release of Claude 3.7 Sonnet,[1] an Anthropic employee started livestreaming Claude trying to play through Pokémon Red. The livestream is still going right now. TL:DR: So, how's it doing? Well, pretty badly. Worse than a 6-year-old would, definitely not PhD-level. Digging in But wait! you say. Didn't Anthropic publish a benchmark showing Claude isn't half-bad at Pokémon? Why yes they did: and the data shown is believable. Currently, the livestream is on its third at...

en

0:18

“Methods for strong human germline engineering” by...

LessWrong (Curated & Popular) ·

2025/03/07

Note: an audio narration is not available for this article. Please see the original text. The original text contained 169 footnotes which were omitted from this narration. The original text contained 79 images which were described by AI. --- First published: March 3rd, 2025 Source: https://www.lesswrong.com/posts/2w6hjptanQ3cDyDw7/methods-for-strong-human-germline-engineering --- Narrated by TYPE III AUDIO. --- I...

en

3:49

“Have LLMs Generated Novel Insights?” by abramdemski,...

LessWrong (Curated & Popular) ·

2025/03/06

In a recent post, Cole Wyeth makes a bold claim: . . . there is one crucial test (yes this is a crux) that LLMs have not passed. They have never done anything important. They haven't proven any theorems that anyone cares about. They haven't written anything that anyone will want to read in ten years (or even one year). Despite apparently memorizing more information than any human could ever dream of, they have made precisely zero novel connections or insights in any area of science[3]. I ...

en

18:47

“A Bear Case: My Predictions Regarding AI Progress”...

LessWrong (Curated & Popular) ·

2025/03/06

This isn't really a "timeline", as such – I don't know the timings – but this is my current, fairly optimistic take on where we're heading. I'm not fully committed to this model yet: I'm still on the lookout for more agents and inference-time scaling later this year. But Deep Research, Claude 3.7, Claude Code, Grok 3, and GPT-4.5 have turned out largely in line with these expectations[1], and this is my current baseline prediction. The Current Paradigm: I'm Tucking In to Sleep I expect th...

en

17:33

“Statistical Challenges with Making Super IQ babies”...

LessWrong (Curated & Popular) ·

2025/03/05

This is a critique of How to Make Superbabies on LessWrong. Disclaimer: I am not a geneticist[1], and I've tried to use as little jargon as possible. so I used the word mutation as a stand in for SNP (single nucleotide polymorphism, a common type of genetic variation). Background The Superbabies article has 3 sections, where they show: Why: We should do this, because the effects of editing will be bigHow: Explain how embryo editing could work, if academia was not mind killed (hampered ...

en

1:51

“Self-fulfilling misalignment data might be poisoning...

LessWrong (Curated & Popular) ·

2025/03/04

This is a link post.Your AI's training data might make it more “evil” and more able to circumvent your security, monitoring, and control measures. Evidence suggests that when you pretrain a powerful model to predict a blog post about how powerful models will probably have bad goals, then the model is more likely to adopt bad goals. I discuss ways to test for and mitigate these potential mechanisms. If tests confirm the mechanisms, then frontier labs should act quickly to break the self-fulfil...

en

11:13

“Judgements: Merging Prediction & Evidence” by...

LessWrong (Curated & Popular) ·

2025/03/01

I recently wrote about complete feedback, an idea which I think is quite important for AI safety. However, my note was quite brief, explaining the idea only to my closest research-friends. This post aims to bridge one of the inferential gaps to that idea. I also expect that the perspective-shift described here has some value on its own. In classical Bayesianism, prediction and evidence are two different sorts of things. A prediction is a probability (or, more generally, a probability distrib...

en

12:31

“The Sorry State of AI X-Risk Advocacy, and Thoughts...

LessWrong (Curated & Popular) ·

2025/02/26

First, let me quote my previous ancient post on the topic: Effective Strategies for Changing Public Opinion The titular paper is very relevant here. I'll summarize a few points. The main two forms of intervention are persuasion and framing.Persuasion is, to wit, an attempt to change someone's set of beliefs, either by introducing new ones or by changing existing ones.Framing is a more subtle form: an attempt to change the relative weights of someone's beliefs, by empathizing different asp...

en

27:11

“Power Lies Trembling: a three-book review” by...

LessWrong (Curated & Popular) ·

2025/02/26

In a previous book review I described exclusive nightclubs as the particle colliders of sociology—places where you can reliably observe extreme forces collide. If so, military coups are the supernovae of sociology. They’re huge, rare, sudden events that, if studied carefully, provide deep insight about what lies underneath the veneer of normality around us. That's the conclusion I take away from Naunihal Singh's book Seizing Power: the Strategic Logic of Military Coups. It's not a conclusion...

en

7:58

“Emergent Misalignment: Narrow finetuning can produce...

LessWrong (Curated & Popular) ·

2025/02/26

This is the abstract and introduction of our new paper. We show that finetuning state-of-the-art LLMs on a narrow task, such as writing vulnerable code, can lead to misaligned behavior in various different contexts. We don't fully understand that phenomenon. Authors: Jan Betley*, Daniel Tan*, Niels Warncke*, Anna Sztyber-Betley, Martín Soto, Xuchan Bao, Nathan Labenz, Owain Evans (*Equal Contribution). See Twitter thread and project page at emergent-misalignment.com. Abstract We present ...

en

42:06

“The Paris AI Anti-Safety Summit” by Zvi

LessWrong (Curated & Popular) ·

2025/02/22

It doesn’t look good. What used to be the AI Safety Summits were perhaps the most promising thing happening towards international coordination for AI Safety. This one was centrally coordination against AI Safety. In November 2023, the UK Bletchley Summit on AI Safety set out to let nations coordinate in the hopes that AI might not kill everyone. China was there, too, and included. The practical focus was on Responsible Scaling Policies (RSPs), where commitments were secured from the major...

en

693 results

Similar Podcasts

Merge Conflict

soundbite.fm

What"s Next with Aki Anastasiou

What"s Next

The Good Tech Companies

HackerNoon

Asynchronous & Unreliable - Conversations on The Edge of Software

Anne Currie

Les Technos

Les Technos Team