PODCAST

LessWrong (30+ Karma)

LessWrong

Audio narrations of LessWrong posts.

technology philosophy

All Episodes

5:42

“Not all capabilities will be created equal: focus on...

LessWrong (30+ Karma) ·

2025/02/13

When, exactly, should we consider humanity to have properly "lost the game", with respect to agentic AI systems?The most common AI milestone concepts seem to be "artificial general intelligence", followed closely by "superintelligence". Sometimes people talk about "transformative AI", "high-level machine intelligence", or "full automation of the labor force." None of these are well-suited for pointing specifically at the capabilities that would spell a "point of no return" for humanity. In fact,

en-gb

2:04

“Utility Engineering: Analyzing and Controlling...

LessWrong (30+ Karma) ·

2025/02/12

This is a link post. As AIs rapidly advance and become more agentic, the risk they pose is governed not only by their capabilities but increasingly by their propensities, including goals and values. Tracking the emergence of goals and values has proven a longstanding problem, and despite much interest over the years it remains unclear whether current AIs have meaningful values. We propose a solution to this problem, leveraging the framework of utility functions to study the internal coherence of AI

en-gb

11:07

“Proof idea: SLT to AIT” by Lucius Bushnaq

LessWrong (30+ Karma) ·

2025/02/11

Audio note: this article contains 60 uses of latex notation, so the narration may be difficult to follow. There's a link to the original text in the episode description. I think we may be able to prove that Bayesian learning on recurrent neural networks is equivalent to a bounded form of Solomonoff Induction, linking Singular Learning Theory (SLT) back to basic Algorithmic Information Theory (AIT). This post is my current early-stage sketch of the proof idea. Don't take it too seriously yet. I’m

en-gb

2:38

“The News is Never Neglected” by lsusr

LessWrong (30+ Karma) ·

2025/02/11

Dear Lsusr,I am inspired by your stories about Effective Evil. My teachers at school told me I should watch the news so I could be a good civic participant. Should I reverse this advice? Or should I watch the news like everyone else, except use what I learn for evil?Sincerely,[redacted]Dear [redacted],If you want to make an impact on the world, then you should put your effort into solving problems that are important, neglected and tractable.Mainstream news often reports on events that are important

en-gb

2:48

“Nonpartisan AI safety” by Yair Halberstadt

LessWrong (30+ Karma) ·

2025/02/11

AI alignment is probably the most pressing issue of our time. Unfortunately it's also become one of the most controversial, with AI accelerationists accusing AI doomers/ai-not-kill-everyoneism-ers of being luddites who would rather keep humanity shackled to the horse and plow than risk any progress, whilst the doomers in turn accuse accels of rushing humanity as fast as it can straight off a cliff.As Robin Hanson likes to point out, trying to change policy on a polarised issue is backbreaking work

en-gb

11:16

“Knocking Down My AI Optimist Strawman” by tailcalled

LessWrong (30+ Karma) ·

2025/02/11

I recently posted my model of an optimistic view of AI, asserting that I disagree with every sentence of it. I thought I might as well also describe my objections to those sentences: "The rapid progress spearheaded by OpenAI is clearly leading to artificial intelligence that will soon surpass humanity in every way."Here's some of the main things humanity might want to achieve: Curing aging and other diseasesPlentiful clean energy from e.g. nuclear fusionDe-escalating nuclear MAD while extending

en-gb

11:42

“Why Did Elon Musk Just Offer to Buy Control of...

LessWrong (30+ Karma) ·

2025/02/11

This is the full text of a post from "The Obsolete Newsletter," a Substack that I write about the intersection of capitalism, geopolitics, and artificial intelligence. I’m a freelance journalist and the author of a forthcoming book called Obsolete: Power, Profit, and the Race to build Machine Superintelligence. Consider subscribing to stay up to date with my work. Wow. The Wall Street Journal just reported that, "a consortium of investors led by Elon Musk is offering $97.4 billion to buy the

en-gb

18:38

“Reasons-based choice and cluelessness” by JesseClifton

LessWrong (30+ Karma) ·

2025/02/10

Crossposted from my Substack. Rational choice theory is commonly thought of as being about what to do in light of our beliefs and preferences. But our beliefs and preferences come from somewhere. I would say that we believe and prefer things for reasons. My evidence gives me reason to believe I am presently in an airport. Any reason I have to think a coin will land heads applies to tails, too, so I should have the same degree of belief in each. The suffering I expect to be averted by donating to

en-gb

4:12

“Gary Marcus now saying AI can’t do things it can...

LessWrong (30+ Karma) ·

2025/02/09

This is a link post.January 2020, Gary Marcus wrote GPT-2 And The Nature Of Intelligence, demonstrating a bunch of easy problems that GPT-2 couldn’t get right.He concluded these were “a clear sign that it is time to consider investing in different approaches.”Two years later, GPT-3 could get most of these right.Marcus wrote a new list of 15 problems GPT-3 couldn’t solve, concluding “more data makes for a better, more fluent approximation to language; it does not make for trustworthy intelligence.”A

en-gb

25:36

“Two hemispheres - I do not think it means what you...

LessWrong (30+ Karma) ·

2025/02/09

I am going to address some misconceptions about brain hemispheres -- in popular culture, and in Zizian theory. The latter, because the madness must stop. The former, because it provided a foundation for the latter.*About 99% of animals are bilaterally symmetric -- the left side and the right side of the body are approximately each other's mirror images. The symmetry is not perfect. For example the human heart is situated slightly on the left side, and its left and right halves have slightly

en-gb

9:06

“‘Think it Faster’ worksheet” by Raemon

LessWrong (30+ Karma) ·

2025/02/09

This is a succinct worksheet version of the "Think It Faster" Exercise. You can use this worksheet either for purposeful practice, after completing some kind of challenging/confusing intellectual exercise (such as Thinking Physics or Baba is You). Or, if in your real life work you find something took a noticeably long time to figure out, or you were surprised about something you might have been able to notice.The goal is to identify: skills you can trainprinciples you can applyactions you can take

en-gb

23:41

“A Problem to Solve Before Building a Deception...

LessWrong (30+ Karma) ·

2025/02/08

TL;DR: If you are thinking of using interpretability to help with strategic deception, then there's likely a problem you need to solve first: how are intentional descriptions (like deception) related to algorithmic ones (like understanding the mechanisms models use)? We discuss this problem and try to outline some constructive directions. 1. IntroductionA commonly discussed AI risk scenario is strategic deception: systems that execute sophisticated planning against their creators to achieve

en-gb

13:45

“Wild Animal Suffering Is The Worst Thing In The...

LessWrong (30+ Karma) ·

2025/02/08

Crossposted from my blog which many people are saying you should check out! Imagine that you came across an injured deer on the road. She was in immense pain, perhaps having been mauled by a bear or seriously injured in some other way. Two things are obvious: If you could greatly help her at small cost, you should do so.Her suffering is bad.In such a case, it would be callous to say that the deer's suffering doesn’t matter because it's natural. Things can both be natural and bad—malaria certainly

en-gb

118:52

“Research directions Open Phil wants to fund in...

LessWrong (30+ Karma) ·

2025/02/08

Open Philanthropy has just launched a large new Request for Proposals for technical AI safety research. Here we're sharing a reference guide, created as part of that RFP, which describes what projects we'd like to see across 21 research directions in technical AI safety. This guide provides an opinionated overview of recent work and open problems across areas like adversarial testing, model transparency, and theoretical approaches to AI alignment. We link to hundreds of papers and blog posts and

en-gb

13:48

“Racing Towards Fusion and AI” by Jeffrey Heninger

LessWrong (30+ Karma) ·

2025/02/08

Racing Towards a New Technology Is a Collective Choice, Not an Inevitable Consequence of Incentives Before I started thinking about AI policy, I was working in the trying-to-get-fusion industry.There are some significant similarities between AI and fusion. Both are emerging technologies.Both have the potential to have significant effects on the global economy.Both are dominated by O(10) major actors, which include both private companies and governments.Both currently require a capital expenditure

en-gb

7:11

“So You Want To Make Marginal Progress...” by...

LessWrong (30+ Karma) ·

2025/02/08

Once upon a time, in ye olden days of strange names and before google maps, seven friends needed to figure out a driving route from their parking lot in San Francisco (SF) down south to their hotel in Los Angeles (LA).The first friend, Alice, tackled the “central bottleneck” of the problem: she figured out that they probably wanted to take the I-5 highway most of the way (the blue 5's in the map above). But it took Alice a little while to figure that out, so in the meantime, the rest of the friends

en-gb

61:33

“How AI Takeover Might Happen in 2 Years” by joshc

LessWrong (30+ Karma) ·

2025/02/07

I’m not a natural “doomsayer.” But unfortunately, part of my job as an AI safety researcher is to think about the more troubling scenarios.I’m like a mechanic scrambling last-minute checks before Apollo 13 takes off. If you ask for my take on the situation, I won’t comment on the quality of the in-flight entertainment, or describe how beautiful the stars will appear from space.I will tell you what could go wrong. That is what I intend to do in this story.Now I should clarify what this is exactly

en-gb

3:31

“Open Philanthropy Technical AI Safety RFP - $40M...

LessWrong (30+ Karma) ·

2025/02/06

This is a link post. Open Philanthropy Technical AI Safety RFP - $40M Available Across 21 Research AreasOpen Philanthropy is launching a big new Request for Proposals for technical AI safety research, with plans to fund roughly $40M in grants over the next 5 months, and available funding for substantially more depending on application quality. Applications (here) start with a simple 300 word expression of interest and are open until April 15, 2025. OverviewWe're seeking proposals across 21 different

en-gb

16:06

“MATS Applications + Research Directions I’m...

LessWrong (30+ Karma) ·

2025/02/06

I've just opened summer MATS applications (where I'll supervise people to write mech interp papers) I'd love to get applications from any readers who are interested! Apply here, due Feb 28As part of this, I wrote up a list of research areas I'm currently excited about, and thoughts for promising directions within those, which I thought might be of wider interest, so I've copied it in below: Understanding thinking models Eg o1, r1, Gemini Flash Thinking, etc - ie models that produce a really long

en-gb

4:42

“Detecting Strategic Deception Using Linear Probes”...

LessWrong (30+ Karma) ·

2025/02/06

This is a link post.Can you tell when an LLM is lying from the activations? Are simple methods good enough? We recently published a paper investigating if linear probes detect when Llama is deceptive.Abstract:AI models might use deceptive strategies as part of scheming or misaligned behaviour. Monitoring outputs alone is insufficient, since the AI might produce seemingly benign outputs while its internal reasoning is misaligned. We thus evaluate if linear probes can robustly detect deception by

en-gb

4,491 results

LessWrong (30+ Karma)

All Episodes

Similar Podcasts

The Automated Daily

TrendTeller

All On AI

All On AI

Elon Musk Podcast

Stage Zero

Reflections

Livewire Labs

科技早8点

之远不知远