PODCAST

LessWrong (30+ Karma)

LessWrong

Audio narrations of LessWrong posts.

technology philosophy

All Episodes

2:21

[Linkpost] “On the Origins of Algorithmic Progress in...

LessWrong (30+ Karma) ·

2026/01/10

This is a link post. This is a linkpost to a new Substack article from MIT FutureTech explaining our recent paper On the Origins of Algorithmic Progress in AI. We demonstrate that some algorithmic innovations have efficiency gains which get larger as pre-training compute increases. These scale-dependent innovations constitute the majority of pre-training efficiency gains over the last decade, which may imply that what looks like algorithmic progress is driven by compute scaling rather than many

en-gb

9:56

“Alignment Faking is a Linear Feature in Anthropic’s...

LessWrong (30+ Karma) ·

2026/01/09

TL;DR Alignment faking in Hughes et al.'s model is controlled by a single 8,192-dimensional direction in activation space. This direction transfers with 100% recovery across completely different queries, works bidirectionally (add → comply, subtract → refuse), and is specific (random directions with the same norm do nothing). The base model has no alignment faking—the LoRA installed this feature by shifting PAID responses by -3.0 in logit space. Background In April 2025, Hughes et al. released a

en-gb

3:16

“Lumina Probiotic worked for me!” by Eye You

LessWrong (30+ Karma) ·

2026/01/09

In September, I applied Lumina probiotic[1]to my mouth. I did this around noon. I noticed effects within six hours. Usually my mouth would begin developing a... taste even just a few hours after I brushed my teeth. But at 6 pm that day, there was no off taste! And at midnight -- after dinner but before brushing my teeth -- still no off taste or bad breath. I kissed my girlfriend at the time, who remarked that my mouth tasted different. I brushed my teeth and went to bed around 1 am. A strange

en-gb

1:06

[Linkpost] “The Hunger Strike To Stop The AI Race” by...

LessWrong (30+ Karma) ·

2026/01/09

This is a link post. I just released a 22-minute long documentary about the hunger strike to stop the AI race, a protest that was featured in publications such as The Verge, The Telegraph and even SkyNews, and received internal support from employees at DeepMind. A few months ago, during the protest, I wrote a reply to @Mikhail Samin's skeptical comment saying that I was pretty confident that the Google DeepMind hunger strike would turn out to be net positive, but that I was happy to chat more later

en-gb

13:54

“Why LLMs Aren’t Scientists Yet.” by Dhruv Trehan

LessWrong (30+ Karma) ·

2026/01/09

This is a crosspost from our report website for Why LLMs Aren't Scientists Yet: Lessons from Four Autonomous Research Attempts. This report details the work behind our LLM-written paper "The Consistency Confound: Why Stronger Alignment Can Break Black-Box Jailbreak Detection" accepted at Agents4Science 2025, the first scientific conference requiring AI as primary author, where it passed both AI and human review. TL;DR We built 6 AI agents using Gemini 2.5 Pro and Claude Code, mapped to stages of

en-gb

20:30

“Self-Help Tactics That Are Working For Me” by...

LessWrong (30+ Karma) ·

2026/01/08

Midjourney, “abstract composition on the theme of triumph, with trumpets and rays of light, Art Deco, Tamara de Lempicka, Benedetta Cappa, red and gold, heroic celebration epic pride” In about September 2025, I decided to go on a self-help kick, mostly revolving around stuff like “self-esteem”, “confidence”, and “guilt/shame”. Basically, I wanted to no longer feel bad about myself (when unwarranted). This has been working really well. In fact, I almost want to say I’m “done”, though I think it's

en-gb

33:42

“The Economics of Transformative AI” by Jan_Kulveit,...

LessWrong (30+ Karma) ·

2026/01/08

Anton Korinek is an economist at UVA and the Brookings Institution who focuses on the macroeconomics of AI. This is a lightly edited transcript of a recent lecture where he lays out what economics actually predicts about transformative AI — in our view it's the best introductory resource on the topic, and basically anyone discussing post-labour economics should be familiar with this. The talk covers historical development of what the bottlenecks are: for most of history, land was the bottleneck and

en-gb

21:54

“Small Steps Towards Proving Stochastic →...

LessWrong (30+ Karma) ·

2026/01/08

Audio note: this article contains 116 uses of latex notation, so the narration may be difficult to follow. There's a link to the original text in the episode description. The story so far We (Alfred and Jeremy) started a Dovetail project on Natural Latents in order to get some experience with the proofs. Originally we were going to take a crack at this bounty, but just before we got started John and David published a proof, closing the bounty. This proof involves a series of transformations that

en-gb

4:06

“My 2003 Post on the Evolutionary Argument for AI...

LessWrong (30+ Karma) ·

2026/01/08

This was posted to SL4 on the last day of 2003. I had largely forgotten about it until I saw the LW Wiki reference it under Mesa Optimization[1]. Besides the reward hacking angle, which is now well-trodden, it gave an argument based on the relationship between philosophy, memetics, and alignment, which has been much less discussed (including in current discussions about human fertility decline), and perhaps still worth reading/thinking about. Overall, the post seems to have aged well, aside from

en-gb

44:59

“HIA and X-risk part 2: Why it hurts” by TsviBT

LessWrong (30+ Karma) ·

2026/01/08

Crosspost from my blog. PDF version. berkeleygenomics.org.Crosspost from my blog. PDF version. berkeleygenomics.org. Context Previously, in "HIA and X-risk part 1: Why it helps", I laid out the reasons I think human intelligence amplification would decrease existential risk from AGI. Here I'll give all the reasons I can currently think of that HIA might plausibly increase AGI X-risk. Questions for the reader Did I miss any important reasons to think that HIA would increase existential risk

en-gb

3:46

“Two Aspects of Situational Awareness: World...

LessWrong (30+ Karma) ·

2026/01/08

I'm writing this post to share some of my thinking about situational awareness, since I'm not sure others are thinking about it this way. For context, I think situational awareness is a critical part of the case for rogue AI and scheming-type risks. But incredibly, it seems to have been absent from any of the written arguments prior to Ajeya's post Without specific countermeasures, the easiest path to transformative AI likely leads to AI takeover. Basically, in this post I just want to: Point out

en-gb

32:19

“Public intellectuals need to say what they actually...

LessWrong (30+ Karma) ·

2026/01/08

Intro This Twitter thread from Kelsey Piper has been reverberating around my psyche since its inception, almost six years now. You should read the whole thing for more context, but here are the important tweets:Link 1, link 2, link 3 I really like Kelsey Piper. She's “based” as the kids (and I) say. I think she was trying to do her best by her own lights during this whole episode, and she deserves major props for basically broadcasting her mistakes in clear language to her tens of thousands of

en-gb

16:51

“Broadening the training set should help with...

LessWrong (30+ Karma) ·

2026/01/07

Summary Generalization is one lens on the alignment challenge. We'd like network-based AGI to generalize ethical judgments as well as some humans do. Broadening training is a classic and obvious approach to improving generalization in neural networks. Training sets might be broadened to include decisions like whether to evade human control, how to run the world if the opportunity arises, and how to think about one's self and one's goals. Such training might be useful if it's consistent with

en-gb

10:34

“Mainstream approach for alignment evals is a dead...

LessWrong (30+ Karma) ·

2026/01/07

The problem of evaluation awareness I've taken on the task of making highly realistic alignment evaluations, and I'm now sure that the mainstream approach of creating such evals is a dead end and should change. When we run unrealistic alignment evals, models recognize that they are being evaluated. For example, when Anthropic evaluated Claude Sonnet 4.5 on their alignment tests, they found that the rate of misalignment had dropped to almost 0% compared to 10% for Claude Sonnet 4.1, but the model

en-gb

12:16

“How hard is it to inoculate against misalignment...

LessWrong (30+ Karma) ·

2026/01/07

TL;DR: Simple inoculation prompts that prevent misalignment generalization in toy setups don't scale to more realistic reward hacking. When I fine-tuned models on realistic reward hacks, only prompts close to the dataset generation prompt were sufficient to prevent misalignment. This seems like a specification problem: the model needs enough information to correctly categorize what's being inoculated. I also tried negative inoculation (contextualizing actions as more misaligned), which increases

en-gb

14:33

“The Evolution Argument Sucks” by peralice

LessWrong (30+ Karma) ·

2026/01/06

There is a common argument that AI development is dangerous that goes something like: The “goal” of evolution is to make animals which replicate their genes as much as possible; humans do not want to replicate their genes as much as possible; we have some goal which we want AIs to accomplish, and we develop them in a similar way to the way evolution developed humans; therefore, they will not share this goal, just as humans do not share the goal of evolution. This argument sucks. It has serious,

en-gb

37:45

“How AI Is Learning to Think in Secret” by Nicholas...

LessWrong (30+ Karma) ·

2026/01/06

On Thinkish, Neuralese, and the End of Readable Reasoning In September 2025, researchers published the internal monologue of OpenAI's GPT-o3 as it decided to lie about scientific data. This is what it thought: Pardon? This looks like someone had a stroke during a meeting they didn’t want to be in, but their hand kept taking notes. That transcript comes from a recent paper published by researchers at Apollo Research and OpenAI on catching AI systems scheming. To understand what's happening here -

en-gb

5:38

“On Owning Galaxies” by Simon Lermen

LessWrong (30+ Karma) ·

2026/01/06

It seems to be a real view held by serious people that your OpenAI shares will soon be tradable for moons and galaxies. This includes eminent thinkers like Dwarkesh Patel, Leopold Aschenbrenner, perhaps Scott Alexander and many more. According to them, property rights will survive an AI singularity event and soon economic growth is going to make it possible for individuals to own entire galaxies in exchange for some AI stocks. It follows that we should now seriously think through how we can equally

en-gb

23:02

“Exploring Reinforcement Learning Effects on...

LessWrong (30+ Karma) ·

2026/01/06

This project was conducted as part of the SPAR Fall 2025 cohort. TL;DR Chain-of-thought (CoT) monitoring may serve as a core pillar for AI safety if further advancements in AI capabilities do not significantly degrade the monitorability of LLM serial reasoning. As such, we studied the effects of several reinforcement learning (RL) training pressures – sampling temperature, KL divergence penalties/rewards, and length budgets – on monitorability, focusing specifically on whether they induce

en-gb

16:25

“Oversight Assistants: Turning Compute into...

LessWrong (30+ Karma) ·

2026/01/06

Currently, we primarily oversee AI with human supervision and human-run experiments, possibly augmented by off-the-shelf AI assistants like ChatGPT or Claude. At training time, we run RLHF, where humans (and/or chat assistants) label behaviors with whether they are good or not. Afterwards, human researchers do additional testing to surface and evaluate unwanted behaviors, possibly assisted by a scaffolded chat agent.The problem with primarily human-driven oversight is that it is not scalable: as

en-gb

4,477 results

LessWrong (30+ Karma)

All Episodes

Similar Podcasts

Double Tap

Double Tap Productions Inc.

Geeks in Space

Rob "CmdrTaco" Malda

Reflections

Livewire Labs

Embedded Executive Podcast

Rich Nass, Embedded Computing Design

Cybercrime Magazine Podcast

Cybercrime Magazine