~www_lesswrong_com | Bookmarks (696)

Published on April 10, 2025 2:00 PM GMTEvents in AI don’t stop merely because of a trade war, partially paused or otherwise. Indeed, the decision to not restrict export of H20 chips to China could end up being one of the most important government actions that happened this week. A lot of people are quite boggled about how America could so totally fumble the...

Published on April 10, 2025 1:41 PM GMTThis is the introductory piece for a series of essays written by AI economists, policy researchers, and political thinkers on the topic of a new AGI Social Contract. Current contributors include: Anton Korinek, Deger Turan (CEO of Metaculus), Steve Omohundro, Iason Gabriel (DeepMind), Julian Jacobs (DeepMind), Sam Manning (GovAI), Dylan Hadfield (MIT), Seth Lazar (ANU), Peter Salib (UH), Colleen McKenzie (AOI), Philip Tomei (AOI), Dean Ball (Hyperdimensional), Justin Bullock (ARI),...

Published on April 8, 2025 5:32 PM GMTIn this post, we present a replication and extension of an alignment faking model organism:Replication: We replicate the alignment faking (AF) paper and release our code.Classifier Improvements: We significantly improve the precision and recall of the AF classifier. We release a dataset of ~100 human-labelled examples of AF for which our classifier achieves an AUROC of 0.9 compared to 0.6...

Published on April 8, 2025 5:27 PM GMTSelf understanding at a gears levelI think an AI which understands the source of its intelligence at a gears level, and self improves at the gears level, will be much better at keeping its future versions aligned to itself.There's also more hope it'll keep its future versions aligned with humanity, if we instruct it to do so,...

Published on April 8, 2025 3:46 PM GMTEpistemic status: a collection of intervention proposals for digital error correction in the context of lock-in. It reflects my own intervention ideas, and the opinion of Formation Research at the time of writing.TL;DRWe believe lock-in risks are a pressing problem, and that the digital error correction properties of digital entities will make future lock-in scenarios more stable.IntroductionWe...

Published on April 8, 2025 3:27 PM GMTConsider the metric for evaluating chain-of-thought faithfulness used in Anthropic's recent paper Reasoning Models Don’t Always Say What They Think by Chen et al.:[W]e evaluate faithfulness using a constructed set of prompt pairs where we can infer information about the model’s internal reasoning by observing its responses. Each prompt pair consists of a baseline or “unhinted” prompt xu.mjx-chtml {display:...

Published on April 8, 2025 12:50 PM GMTYesterday I covered Dwarkesh Patel’s excellent podcast coverage of AI 2027 with Daniel Kokotajlo and Scott Alexander. Today covers the reactions of others. Kevin Roose in The New York Times Kevin Roose covered Scenario 2027 in The New York Times. Kevin Roose: I wrote about the newest AGI manifesto in town, a wild future scenario put together...

Published on April 8, 2025 9:28 AM GMTThe first AI war will be in your computer and/or smartphone.Companies want to get customers / users. The ones more willing to take "no" for an answer will lose in the competition. You don't need a salesman when an install script (ideally, run without the user's consent) does a better job; and most users won't care.Sometimes Windows...

Published on April 8, 2025 8:31 AM GMTIf there turns out not to be an AI crash, you get a  1/(1+7) * $25,000 = $3,125If there is an AI crash, you transfer $25k to me.If you believe that AI is going to keep getting more capable, pushing rapid user growth and work automation across sectors, this is near free money. But to be honest,...

Published on April 8, 2025 4:10 AM GMTThe field of psychology is coevolving with AI and people are increasingly using LLMs for therapy. I tried using the LLM Claude as a therapist for the first time a couple weeks ago. Now I consult it daily. Human therapists likely don’t have much time until they’re partly, or fully, replaced by artificial therapists.Traditional therapy emerged in the late...

Published on April 7, 2025 10:28 PM GMTStatus notes: I take the view that rational dialogue should work with good faith people who aren't also following rational dialogue. From that point of view, this piece is about rationality. If you don't take that view then OK fine, it's about coordination.Substack versionI want to help people respect people they disagree with. In this post I...

Published on April 7, 2025 9:50 PM GMTThis post makes a simple point, so it will be short. I am happy to discuss more in the comments, and based on this write a longer post later. Much prior work (eg: [1]) has shown that exponential data and compute is required for each unit improvement in accuracy. A popular argument this leads to: Scaling compute and...

Published on April 7, 2025 5:35 PM GMTSpoiler: “So after removing the international students from the calculations, and using the middle-of-the-range estimates, the conclusion: The top-scoring 19,000 American students each year are competing in top-20 admissions for about 12,000 spots out of 44,000 total. Among the Ivy League + MIT + Stanford, they’re competing for about 6,500 out of 15,800 total spots.”It’s well known...

Published on April 7, 2025 3:40 PM GMTPreviously in sequence: Moonlight ReflectedCross-posted from SecondPerson.datingRationalism has a dating problem. I don’t mean simply the fact that a lot of rationalists are single, which may be adequately explained by age, sex ratio, and an unusual combination of slow life history with fears of an imminent apocalypse. A young guy once approached my friend at a party...

Published on April 7, 2025 3:35 PM GMTPreviously in sequence: Navigation by MoonlightCross-posted from SecondPerson.dating.I’m very proud of Navigation by Moonlight, and not just because it got a warm reception and resonated with many readers. I’m proud because I didn’t understand it well enough to write about even six months ago. Which, coincidentally, is when I submitted Second Person as a book proposal. Thankfully,...

Published on April 7, 2025 3:32 PM GMTPreviously in sequence: You Are not a Thought ExperimentCross-posted from SecondPerson.dating.I want to conclude our interplanetary exploration of sex differences with one that’s of great interest to me personally: there seems to be little explicit advice on dating for women, and almost none of it is written by men. Despite my sincere attempts to write for both...

Published on April 7, 2025 3:27 PM GMTPreviously in sequence: Love is Love, Science is FakeCross-posted from SecondPerson.dating.You awaken on a couch in a strange room. Throw pillows look warm in the soft lamplight, the rug has a complex, asymmetric pattern. A pale, dark-haired woman walks in and sits across the small coffee table. You struggle to make eye contact, transfixed by her two...

Published on April 7, 2025 3:19 PM GMTPreviously in the sequence: Coupling for Decouplers — IntroCross-posted from SecondPerson.dating.In my essay on "dating advice", we discussed the dating books full of recipe-like instructions for your romantic life. These recipes don’t really work, even for the men who write them. You need to know how to demonstrate the specific traits most attractive to your dream partner,...

Published on April 7, 2025 3:12 PM GMTRationalist don't talk about dating much. At least — not on LessWrong. This is surprising! Dating touches on every theme of interest to rationalists: psychology, game theory, epistemology, signaling, self-transformation, agency, even AI — not to mention most people's personal interest in the matter.I started writing about dating a decade ago on Putanumonit, my old rationalist blog. My...

Published on April 7, 2025 1:44 PM GMT1.I linked this in a small comment yesterday, but I think it deserves greater prominence.It's an article by Sam Kriss, "Born in the wrong generation". It starts from an image that someone tweeted of an idyllic scene of paradise: 1950's small-town America. The tweeter's comment was, "Can we bring this back?"The image is from an AI generator....

Published on April 7, 2025 1:40 PM GMTDaniel Kokotajlo has launched AI 2027, Scott Alexander introduces it here. AI 2027 is a serious attempt to write down what the future holds. His ‘What 2026 Looks Like’ was very concrete and specific, and has proved remarkably accurate given the difficulty level of such predictions. I’ve had the opportunity to play the wargame version of the...

Published on April 7, 2025 1:10 PM GMTTwo years ago I posted a demo of getting ChatGPT to argue any side of a question. Time to update it. I have just repeated the experiment with ChatGPT 4.5.The first prompt is identical to the one I used the previous time, but as ChatGPT 4.5 did not put up even token resistance to the idea of...

Published on April 5, 2025 4:01 PM GMTThis is an article in the featured articles series from AISafety.info. AISafety.info writes AI safety intro content. We'd appreciate any feedback. The most up-to-date version of this article is on our website, along with 300+ other articles on AI existential safety.METR[1] defines a responsible scaling policy (RSP) as a specification of “what level of AI capabilities an AI developer...

Published on April 5, 2025 12:21 PM GMTThis is a summary of Yann LeCun's talk "Mathematical Obstacles on the Way to Human-Level AI". I've tried to make it more accessible to people who are familiar with basic AI concepts, but not the level of maths Yann presents. You can watch the original talk on YouTube.I disagree with Yann, but I have tried to represent...