PODCAST

LessWrong (30+ Karma)

LessWrong

Audio narrations of LessWrong posts.

technology philosophy

All Episodes

34:45

“DeepMind: An Approach to Technical AGI Safety and...

LessWrong (30+ Karma) ·

2025/04/06

I quote the abstract, 10-page "extended abstract," and table of contents. See link above for the full 100-page paper. See also the blogpost (which is not a good summary) and tweet thread. I haven't read most of the paper, but I'm happy about both the content and how DeepMind (or at least its safety team) is articulating an "anytime" (i.e., possible to implement quickly) plan for addressing misuse and misalignment risks. But I think safety at DeepMind is more bottlenecked by buy-in from leadership

en-gb

15:17

“Among Us: A Sandbox for Agentic Deception” by 7vik,...

LessWrong (30+ Karma) ·

2025/04/05

We show that LLM-agents exhibit human-style deception naturally in "Among Us". We introduce Deception ELO as an unbounded measure of deceptive capability, suggesting that frontier models win more because they're better at deception, not at detecting it. We evaluate probes and SAEs to detect out-of-distribution deception, finding they work extremely well. We hope this is a good testbed to improve safety techniques to detect and remove agentically-motivated deception, and to anticipate deceptive

en-gb

8:21

“Alignment faking CTFs: Apply to my MATS stream” by...

LessWrong (30+ Karma) ·

2025/04/05

Right now, alignment seems easy – but that's because models spill the beans when they are misaligned. Eventually, models might “fake alignment,” and we don’t know how to detect that yet. It might seem like there's a swarming research field improving white box detectors – a new paper about probes drops on arXiv nearly every other week. But no one really knows how well these techniques work. Some researchers have already tried to put white box detectors to the test. I built a model organism testbed a

en-gb

7:03

“Meditation and Reduced Sleep Need” by niplav

LessWrong (30+ Karma) ·

2025/04/05

Summary: Meditation may decrease sleep need, and large amounts of meditation may decrease sleep need drastically. Correlation between total sleep duration & time spent meditating is -0.32 including my meditation retreat data, -0.016 excluding the meditation retreat. While it may be true that, when doing intensive practice, the need for sleep may go down to perhaps four to six hour or less at a time, try to get at least some sleep every night. —Daniel Ingram, “Mastering the Core Teachings of

en-gb

17:06

“LLM AGI will have memory, and memory changes...

LessWrong (30+ Karma) ·

2025/04/04

Summary: When stateless LLMs are given memories they will accumulate new beliefs and behaviors, and that may allow their effective alignment to evolve. (Here "memory" is learning during deployment that is persistent beyond a single session.)[1] LLM agents will have memory: Humans who can't learn new things ("dense anterograde amnesia") are not highly employable for knowledge work. LLM agents that can learn during deployment seem poised to have a large economic advantage. Limited memory systems for

en-gb

23:56

“Will compute bottlenecks prevent a software...

LessWrong (30+ Karma) ·

2025/04/04

Epistemic status – thrown together quickly. This is my best-guess, but could easily imagine changing my mind. Intro I recently copublished a report arguing that there might be a software intelligence explosion (SIE) – once AI R&D is automated (i.e. automating OAI), the feedback loop of AI improving AI algorithms could accelerate more and more without needing more hardware. If there is an SIE, the consequences would obviously be massive. You could shoot from human-level to superintelligent AI

en-gb

10:44

“The Rise of Hyperpalatability” by Jack

LessWrong (30+ Karma) ·

2025/04/03

Hello, this is my first post here. I was told by a friend that I should post here. This is from a series of works that I wrote with strict structural requirements. I have performed minor edits to make the essay more palatable for human consumption. This work is an empirical essay on a cycle of hunger to satiatiation to hyperpalatability that I have seen manifested in multiple domains ranging from food to human connection. My hope is that you will gain some measure of appreciation for how we have

en-gb

9:09

“Why Have Sentence Lengths Decreased?” by Arjun...

LessWrong (30+ Karma) ·

2025/04/03

“In the loveliest town of all, where the houses were white and high and the elms trees were green and higher than the houses, where the front yards were wide and pleasant and the back yards were bushy and worth finding out about, where the streets sloped down to the stream and the stream flowed quietly under the bridge, where the lawns ended in orchards and the orchards ended in fields and the fields ended in pastures and the pastures climbed the hill and disappeared over the top toward the

en-gb

3:23

“Announcing ILIAD2: ODYSSEY” by Alexander Gietelink...

LessWrong (30+ Karma) ·

2025/04/03

We are pleased to announce ILIAD2: ODYSSEY—a 5-day conference bringing together 100+ researchers to build scientific foundations for AI alignment. This is the 2nd iteration of ILIAD, which was first held in the summer of 2024. ***Apply to attend by June 1!*** When: Aug 25-29, 2025 Where: @Lighthaven (Berkeley, US) What: Unconference with participant-led programming, 100+ attendees. Who: Currently confirmed attendees include Scott Garrabrant, Daniel Murfet, James Crutchfield, Jesse Hoogland, and

en-gb

54:31

“AI 2027: What Superintelligence Looks Like” by...

LessWrong (30+ Karma) ·

2025/04/03

In 2021 I wrote what became my most popular blog post: What 2026 Looks Like. I intended to keep writing predictions all the way to AGI and beyond, but chickened out and just published up till 2026. Well, it's finally time. I'm back, and this time I have a team with me: the AI Futures Project. We've written a concrete scenario of what we think the future of AI will look like. We are highly uncertain, of course, but we hope this story will rhyme with reality enough to help us all prepare for what's

en-gb

6:37

“How To Believe False Things” by Eneasz

LessWrong (30+ Karma) ·

2025/04/03

Intro [you can skip this section if you don’t need context and just want to know how I could believe such a crazy thing] In my chat community: “Open Play” dropped, a book that says there's no physical difference between men and women so there shouldn’t be separate sports leagues. Boston Globe says their argument is compelling. Discourse happens, which is mostly a bunch of people saying “lololololol great trolling, what idiot believes such obvious nonsense?” I urge my friends to be compassionate to

en-gb

21:49

“Show, not tell: GPT-4o is more opinionated in images...

LessWrong (30+ Karma) ·

2025/04/02

Epistemic status: This should be considered an interim research note. Feedback is appreciated. Introduction We increasingly expect language models to be ‘omni-modal’, i.e. capable of flexibly switching between images, text, and other modalities in their inputs and outputs. In order to get a holistic picture of LLM behaviour, black-box LLM psychology should take into account these other modalities as well. In this project, we do some initial exploration of image generation as a modality for

en-gb

2:14

“Is there instrumental convergence for virtues?” by...

LessWrong (30+ Karma) ·

2025/04/02

A key step in the classic argument for AI doom is instrumental convergence: the idea that agents with many different goals will end up pursuing the same few subgoals, which includes things like "gain as much power as possible".If it wasn't for instrumental convergence, you might think that only AIs with very specific goals would try to take over the world. But instrumental convergence says it's the other way around: only AIs with very specific goals will refrain from taking over the world. For

en-gb

6:17

“Leverage, Exit Costs, and Anger: Re-examining Why We...

LessWrong (30+ Karma) ·

2025/04/02

Let's cut through the comforting narratives and examine a common behavioral pattern with a sharper lens: the stark difference between how anger is managed in professional settings versus domestic ones. Many individuals can navigate challenging workplace interactions with remarkable restraint, only to unleash significant anger or frustration at home shortly after. Why does this disparity exist? Common psychological explanations trot out concepts like "stress spillover," "ego depletion," or the home

en-gb

4:23

“Introducing BenchBench: An Industry Standard...

LessWrong (30+ Karma) ·

2025/04/02

Recent progress in AI has led to rapid saturation of most capability benchmarks - MMLU, RE-Bench, etc. Even much more sophisticated benchmarks such as ARC-AGI or FrontierMath see incredibly fast improvement, and all that while severe under-elicitation is still very salient. As has been pointed out by many, general capability involves more than simple tasks such as this, that have a long history in the field of ML and are therefore easily saturated. Claude Plays Pokemon is a good example of

en-gb

3:32

“PauseAI and E/Acc Should Switch Sides” by WillPetillo

LessWrong (30+ Karma) ·

2025/04/02

In the debate over AI development, two movements stand as opposites: PauseAI calls for slowing down AI progress, and e/acc (effective accelerationism) calls for rapid advancement. But what if both sides are working against their own stated interests? What if the most rational strategy for each would be to adopt the other's tactics—if not their ultimate goals? AI development speed ultimately comes down to policy decisions, which are themselves downstream of public opinion. No matter how compelling

en-gb

10:34

“My ‘infohazards small working group’ Signal Chat may...

LessWrong (30+ Karma) ·

2025/04/02

Remember: There is no such thing as a pink elephant. Recently, I was made aware that my “infohazards small working group” Signal chat, an informal coordination venue where we have frank discussions about infohazards and why it will be bad if specific hazards were leaked to the press or public, accidentally was shared with a deceitful and discredited so-called “journalist,” Kelsey Piper. She is not the first person to have been accidentally sent sensitive material from our group chat, however she is

en-gb

1:40

“Consider showering” by Bohaska

LessWrong (30+ Karma) ·

2025/04/02

I think that rationalists should consider taking more showers.As Eliezer Yudkowsky once said, boredom makes us human. The childhoods of exceptional people often include excessive boredom as a trait that helped cultivate their genius: A common theme in the biographies is that the area of study which would eventually give them fame came to them almost like a wild hallucination induced by overdosing on boredom. They would be overcome by an obsession arising from within. Unfortunately, most people don't

en-gb

6:41

“I’m resigning as Meetup Czar. What’s next?” by...

LessWrong (30+ Karma) ·

2025/04/02

After ~3 years as the ACX Meetup Czar, I've decided to resign from my position, and I intend to scale back my work with the LessWrong community as well. While this transition is not without some sadness, I'm excited for my next project. I'm the Meetup Czar of the new Fewerstupidmistakesity community. We're calling it Fewerstupidmistakesity because people get confused about what "Rationality" means, and this would create less confusion. It would be a stupid mistake to name your philosophical

en-gb

6:36

“Introducing WAIT to Save Humanity” by carterallen

LessWrong (30+ Karma) ·

2025/04/02

The EA/rationality community has struggled to identify robust interventions for mitigating existential risks from advanced artificial intelligence. In this post, I identify a new strategy for delaying the development of advanced AI while saving lives roughly 2.2 million times [-5 times, 180 billion times] as cost-effectively as leading global health interventions, known as the WAIT (Wasting AI researchers' Time) Initiative. This post will discuss the advantages of WAITing, highlight early efforts

en-gb

4,489 results

LessWrong (30+ Karma)

All Episodes

Similar Podcasts

Talking Tech w/ Wayne

Wayne Hunter

The Everything Feed - All Packet Pushers Pods

Packet Pushers

The Good Tech Companies

HackerNoon

Engadget News + Next

Engadget

Cybersecurity Tech Brief By HackerNoon

HackerNoon