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

13:08

“LLM Generality is a Timeline Crux” by eggsyntax

LessWrong (Curated & Popular) ·

2024/06/28

Crossposted from the AI Alignment Forum. May contain more technical jargon than usual. Short SummaryLLMs may be fundamentally incapable of fully general reasoning, and if so, short timelines are less plausible. Longer summaryThere is ML research suggesting that LLMs fail badly on attempts at general reasoning, such as planning problems, scheduling, and attempts to solve novel visual puzzles. This post provides a brief introduction to that research, and asks: Whether this limitation is illusor...

en

17:07

“Formal verification, heuristic explanations and...

LessWrong (Curated & Popular) ·

2024/06/27

ARC's current research focus can be thought of as trying to combine mechanistic interpretability and formal verification. If we had a deep understanding of what was going on inside a neural network, we would hope to be able to use that understanding to verify that the network was not going to behave dangerously in unforeseen situations. ARC is attempting to perform this kind of verification, but using a mathematical kind of "explanation" instead of one written in natural language.To help eluc...

en

13:08

“LLM Generality is a Timeline Crux” by eggsyntax

LessWrong (Curated & Popular) ·

2024/06/25

Summary Summary . LLMs may be fundamentally incapable of fully general reasoning, and if so, short timelines are less plausible. Longer summaryThere is ML research suggesting that LLMs fail badly on attempts at general reasoning, such as planning problems, scheduling, and attempts to solve novel visual puzzles. This post provides a brief introduction to that research, and asks: Whether this limitation is illusory or actually exists.If it exists, whether it will be solved by scaling or is a ...

en

18:29

“SAE feature geometry is outside the superposition...

LessWrong (Curated & Popular) ·

2024/06/25

Summary: Superposition-based interpretations of neural network activation spaces are incomplete. The specific locations of feature vectors contain crucial structural information beyond superposition, as seen in circular arrangements of day-of-the-week features and in the rich structures. We don’t currently have good concepts for talking about this structure in feature geometry, but it is likely very important for model computation. An eventual understanding of feature geometry might look like...

en

17:56

“Connecting the Dots: LLMs can Infer & Verbalize...

LessWrong (Curated & Popular) ·

2024/06/23

Crossposted from the AI Alignment Forum. May contain more technical jargon than usual.This is a link post.TL;DR: We published a new paper on out-of-context reasoning in LLMs. We show that LLMs can infer latent information from training data and use this information for downstream tasks, without any in-context learning or CoT. For instance, we finetune GPT-3.5 on pairs (x,f(x)) for some unknown function f. We find that the LLM can (a) define f in Python, (b) invert f, (c) compose f with other ...

en

2:59

“Boycott OpenAI” by PeterMcCluskey

LessWrong (Curated & Popular) ·

2024/06/21

This is a link post.I have canceled my OpenAI subscription in protest over OpenAI's lack ofethics.In particular, I object to: threats to confiscate departing employees' equity unless thoseemployees signed a life-long non-disparagement contractSam Altman's pattern of lying about important topicsI'm trying to hold AI companies to higher standards than I use fortypical companies, due to the risk that AI companies will exert unusualpower.A boycott of OpenAI subscriptions seems unlikely to gain en...

en

15:37

“Sycophancy to subterfuge: Investigating reward...

LessWrong (Curated & Popular) ·

2024/06/20

Crossposted from the AI Alignment Forum. May contain more technical jargon than usual.This is a link post.New Anthropic model organisms research paper led by Carson Denison from the Alignment Stress-Testing Team demonstrating that large language models can generalize zero-shot from simple reward-hacks (sycophancy) to more complex reward tampering (subterfuge). Our results suggest that accidentally incentivizing simple reward-hacks such as sycophancy can have dramatic and very difficult to rev...

en

7:28

“I would have shit in that alley, too” by Declan Molony

LessWrong (Curated & Popular) ·

2024/06/18

After living in a suburb for most of my life, when I moved to a major U.S. city the first thing I noticed was the feces. At first I assumed it was dog poop, but my naivety didn’t last long.One day I saw a homeless man waddling towards me at a fast speed while holding his ass cheeks. He turned into an alley and took a shit. As I passed him, there was a moment where our eyes met. He sheepishly averted his gaze.The next day I walked to the same place. There are a number of businesses on both sid...

en

35:25

“Getting 50% (SoTA) on ARC-AGI with GPT-4o” by...

LessWrong (Curated & Popular) ·

2024/06/18

ARC-AGI post Getting 50% (SoTA) on ARC-AGI with GPT-4oI recently got to 50%[1] accuracy on the public test set for ARC-AGI by having GPT-4o generate a huge number of Python implementations of the transformation rule (around 8,000 per problem) and then selecting among these implementations based on correctness of the Python programs on the examples (if this is confusing, go here)[2]. I use a variety of additional approaches and tweaks which overall substantially improve the performance of my m...

en

15:19

“Why I don’t believe in the placebo effect” by...

LessWrong (Curated & Popular) ·

2024/06/15

Have you heard this before? In clinical trials, medicines have to be compared to a placebo to separate the effect of the medicine from the psychological effect of taking the drug. The patient's belief in the power of the medicine has a strong effect on its own. In fact, for some drugs such as antidepressants, the psychological effect of taking a pill is larger than the effect of the drug. It may even be worth it to give a patient an ineffective medicine just to benefit from the placebo effect...

en

8:47

“Safety isn’t safety without a social model (or:...

LessWrong (Curated & Popular) ·

2024/06/14

Crossposted from the AI Alignment Forum. May contain more technical jargon than usual.As an AI researcher who wants to do technical work that helps humanity, there is a strong drive to find a research area that is definitely helpful somehow, so that you don’t have to worry about how your work will be applied, and thus you don’t have to worry about things like corporate ethics or geopolitics to make sure your work benefits humanity.Unfortunately, no such field exists. In particular, technical ...

en

7:29

“My AI Model Delta Compared To Christiano” by...

LessWrong (Curated & Popular) ·

2024/06/13

Preamble: Delta vs CruxThis section is redundant if you already read My AI Model Delta Compared To Yudkowsky.I don’t natively think in terms of cruxes. But there's a similar concept which is more natural for me, which I’ll call a delta.Imagine that you and I each model the world (or some part of it) as implementing some program. Very oversimplified example: if I learn that e.g. it's cloudy today, that means the “weather” variable in my program at a particular time[1] takes on the value “clou...

en

7:27

“My AI Model Delta Compared To Yudkowsky” by...

LessWrong (Curated & Popular) ·

2024/06/10

Preamble: Delta vs CruxI don’t natively think in terms of cruxes. But there's a similar concept which is more natural for me, which I’ll call a delta.Imagine that you and I each model the world (or some part of it) as implementing some program. Very oversimplified example: if I learn that e.g. it's cloudy today, that means the “weather” variable in my program at a particular time[1] takes on the value “cloudy”. Now, suppose your program and my program are exactly the same, except that somewh...

en

5:29

“Response to Aschenbrenner’s ‘Situational Awareness’”...

LessWrong (Curated & Popular) ·

2024/06/07

(Cross-posted from Twitter.) My take on Leopold Aschenbrenner's new report: I think Leopold gets it right on a bunch of important counts.Three that I especially care about: Full AGI and ASI soon. (I think his arguments for this have a lot of holes, but he gets the basic point that superintelligence looks 5 or 15 years off rather than 50+.)This technology is an overwhelmingly huge deal, and if we play our cards wrong we're all dead.Current developers are indeed fundamentally unserious about th...

en

5:02

“Humming is not a free $100 bill” by Elizabeth

LessWrong (Curated & Popular) ·

2024/06/07

Last month I posted about humming as a cheap and convenient way to flood your nose with nitric oxide (NO), a known antiviral. Alas, the economists were right, and the benefits were much smaller than I estimated.The post contained one obvious error and one complication. Both were caught by Thomas Kwa, for which he has my gratitude. When he initially pointed out the error I awarded him a $50 bounty; now that the implications are confirmed I’ve upped that to $250. In two weeks an additional $750...

en

4:05

“Announcing ILIAD — Theoretical AI Alignment...

LessWrong (Curated & Popular) ·

2024/06/06

Crossposted from the AI Alignment Forum. May contain more technical jargon than usual.We are pleased to announce ILIAD — a 5-day conference bringing together 100+ researchers to build strong scientific foundations for AI alignment. ***Apply to attend by June 30!*** When: Aug 28 - Sep 3, 2024Where: @Lighthaven (Berkeley, US)What: A mix of topic-specific tracks, and unconference style programming, 100+ attendees. Topics will include Singular Learning Theory, Agent Foundations, Causal Incentives...

en

4:57

“Non-Disparagement Canaries for OpenAI” by aysja,...

LessWrong (Curated & Popular) ·

2024/05/31

Since at least 2017, OpenAI has asked departing employees to sign offboarding agreements which legally bind them to permanently—that is, for the rest of their lives—refrain from criticizing OpenAI, or from otherwise taking any actions which might damage its finances or reputation.[1]If they refused to sign, OpenAI threatened to take back (or make unsellable) all of their already-vested equity—a huge portion of their overall compensation, which often amounted to millions of dollars. Given this...

en

13:46

“MIRI 2024 Communications Strategy” by Gretta Duleba

LessWrong (Curated & Popular) ·

2024/05/30

As we explained in our MIRI 2024 Mission and Strategy update, MIRI has pivoted to prioritize policy, communications, and technical governance research over technical alignment research. This follow-up post goes into detail about our communications strategy. The Objective: Shut it Down[1]Our objective is to convince major powers to shut down the development of frontier AI systems worldwide before it is too late. We believe that nothing less than this will prevent future misaligned smarter-than...

en

66:19

“OpenAI: Fallout” by Zvi

LessWrong (Curated & Popular) ·

2024/05/28

Previously: OpenAI: Exodus (contains links at top to earlier episodes), Do Not Mess With Scarlett JohanssonWe have learned more since last week. It's worse than we knew.How much worse? In which ways? With what exceptions?That's what this post is about. The Story So FarFor years, employees who left OpenAI consistently had their vested equity explicitly threatened with confiscation and the lack of ability to sell it, and were given short timelines to sign documents or else. Those documents cont...

en

1:26

[HUMAN VOICE] Update on human narration for this podcast

LessWrong (Curated & Popular) ·

2024/05/28

Contact: patreon.com/lwcurated or [perrin dot j dot walker plus lesswrong fnord gmail].All Solenoid's narration work found here.

en

601 results

Similar Podcasts

Lead With AI

Tamara Nall

Linux in the Ham Shack

Black Sparrow Media

Data Engineering Podcast

Tobias Macey

Eye On A.I.

Craig S. Smith

Reflections

Livewire Labs