LessWrong (30+ Karma)

We are curious if large language models behave consistently when user prompts contain typos. To explore this, we ran a small experiment injecting typos into BigCodeBench and evaluated several Claude models under increasing noise levels. As the typo rate rose to 16%, Opus’ accuracy dropped by 9%. Surprisingly, Haiku's accuracy increased by 22%. This post examines this unexpected “typo uplift” phenomenon and explores why noise appears to help certain models. Do Typos Make Haiku Try Harder? We first hypothesize that Haiku's capabilities increased because harder-to-read text makes Haiku think harder. This aligns with observed results in humans that difficult fonts make students retain knowledge better, as it forces them to expend more effort. As a proxy for effort, we plotted the number of output tokens generated by both models[1]. Contrary to our hypothesis, the number of output tokens decreased by typo rate. Typos don't make models think harder. As typo rates increase, the output lengths of Haiku and Opus go down. The Anomaly is Haiku-Specific We then tested if other small models have this typo uplift anomaly. We found that both Haiku 3.5 and 4.5 have this effect of increased accuracy as typos increase, while other smaller models from [...] ---Outline:(00:54) Do Typos Make Haiku Try Harder?(01:34) The Anomaly is Haiku-Specific(02:08) The Anomaly is Benchmark-Specific(02:42) The Culprit(04:02) Takeaways for the Eval Engineer(04:06) Not all grading harnesses are created equal(04:48) Scores are lower bounds(05:15) Aligning the model to the eval(05:43) Appendix The original text contained 2 footnotes which were omitted from this narration. --- First published: March 16th, 2026 Source: https://www.lesswrong.com/posts/tcic5c3BJuh3PybDZ/adding-typos-made-haiku-s-accuracy-go-up-1 --- Narrated by TYPE III AUDIO. ---Images from the article:Apple Podcasts and Spotify do not show images in the episode description. Try Pocket Casts, or another podcast app.

Early 2026 LLMs in scaffolds, from simple ones such as giving the model access to a scratchpad/"chain of thought" up to MCP servers, skills, and context compaction &c are quite capable. (Obligatory meme link to the METR graph.) Yet: If someone had told me in 2019 that systems with such capability would exist in 2026, I would strongly predict that they would be almost uncontrollable optimizers, ruthlessly & tirelessly pursuing their goals and finding edge instantiations in everything. But they don't seem to be doing that. Current-day LLMs are just not that optimizer-y, they appear to have capable behavior without apparent agent structure. Discussions from the time either ruled out giant lookup-tables (Altair 2024): One obvious problem is that there could be a policy which is the equivalent of a giant look-up table it's just a list of key-value pairs where the previous observation sequence is the look-up key, and it returns a next action. For any well-performing policy, there could exist a table version of it. These are clearly not of interest, and in some sense they have no "structure" at all, let alone agent structure. A way to filter out the look-up tables is [...] The original text contained 3 footnotes which were omitted from this narration. --- First published: March 17th, 2026 Source: https://www.lesswrong.com/posts/a9KqqgjN8gc3Mzzkh/llms-as-giant-lookup-tables-of-shallow-circuits --- Narrated by TYPE III AUDIO.

Things are relatively quiet on the AI front, so I figured it's time to check in on some other things that have been going on, including various developments at the FDA. Table of Contents FDA Reformandum Est. FDA Delenda Est. IN MICE. Doctor, Doctor. Trust The Process. Cancer Screening. Autism Everywhere All At Once. Other Mental Problems Everywhere All At Once. Source Data Verification. External Review Board. Walk It Off. An Unhealthy Weight Can Be Worse Than You Realize. Our GLP-1 Price Cheap. Right To Die Should Include Right To Try. FDA Reformandum Est In lieu of plan A, how about plan B? Senator Bill Cassidy released a new report on modernizing the FDA. Alex Tabarrok approves, which means it's probably good. The FDA chief has an even better idea. Matthew Herper: FDA chief Marty Makary says ‘everything should be over the counter’ unless drug is unsafe or addictive [or requires monitoring]. Annika Kim Constantino: Makary said the FDA is looking at “basic, safe” prescription drugs like nausea medications and vaginal estrogen, which is used to [...] ---Outline:(00:19) FDA Reformandum Est(01:17) FDA Delenda Est(14:11) IN MICE(15:09) Doctor, Doctor(15:38) Trust The Process(16:51) Cancer Screening(18:18) Autism Everywhere All At Once(19:25) Other Mental Problems Everywhere All At Once(21:26) Source Data Verification(26:18) External Review Board(26:57) Walk It Off(28:16) An Unhealthy Weight Can Be Worse Than You Realize(29:04) Our GLP-1 Price Cheap(30:55) Right To Die Should Include Right To Try --- First published: March 17th, 2026 Source: https://www.lesswrong.com/posts/ypnYfPmn6FqAyxCpJ/medical-roundup-7 --- Narrated by TYPE III AUDIO. ---Images from the article:Apple Podcasts and Spotify do not show images in the episode description. Try Pocket Casts, or another podcast app.

This is a rough draft I'm posting here for feedback. If people like it, a version of it might make it into the next scenario report we write. ... We think it's important for decisionmakers to track whether and when they are handing off to AI systems. We expect this will become a hot-button political topic eventually; people will debate whether we should ever handoff to AIs, and if so how, and when. When someone proposes a plan for how to manage the AI crisis or the AGI transition or whatever it's called, others will ask them “So what does your plan say about handoff?” There are two importantly different kinds of handoff: Handing off trust and handing off decisionmaking. You can have one without the other. Trust-handoff means that you are trusting some AI system or set of AI systems not to screw you over. It means that they totally could screw you over, if they chose to, and therefore you are trusting them not to. Decision-handoff means that you are allowing some AI system or set of AI systems to make decisions autonomously, or de-facto-autonomously (e.g. a human is [...] ---Outline:(02:17) Now for some details and nuance:(07:19) When should we hand off trust and when should we hand off decisionmaking? --- First published: March 16th, 2026 Source: https://www.lesswrong.com/posts/YuMr6kbstuieQHkGj/types-of-handoff-to-ais --- Narrated by TYPE III AUDIO.

In this post, I’m trying to put forward a narrow, pedagogical point, one that comes up mainly when I’m arguing in favor of LLMs having limitations that human learning does not. (E.g. here, here, here.) See the bottom of the post for a list of subtexts that you should NOT read into this post, including “…therefore LLMs are dumb”, or “…therefore LLMs can’t possibly scale to superintelligence”. Some intuitions on how to think about “real” continual learning Consider an algorithm for training a Reinforcement Learning (RL) agent, like the Atari-playing Deep Q network (2013) or AlphaZero (2017), or think of within-lifetime learning in the human brain, which (I claim) is in the general class of “model-based reinforcement learning”, broadly construed. These are all real-deal full-fledged learning algorithms: there's an algorithm for choosing the next action right now, and there's one or more update rules for permanently changing some adjustable parameters (a.k.a. weights) in the model such that its actions and/or predictions will be better in the future. And indeed, the longer you run them, the more competent they get. When we think of “continual learning”, I suggest that those are good central examples to keep in mind. Here are [...] ---Outline:(00:35) Some intuitions on how to think about real continual learning(04:57) Why real continual learning cant be copied by an imitation learner(09:53) Some things that are off-topic for this post The original text contained 3 footnotes which were omitted from this narration. --- First published: March 16th, 2026 Source: https://www.lesswrong.com/posts/9rCTjbJpZB4KzqhiQ/you-can-t-imitation-learn-how-to-continual-learn --- Narrated by TYPE III AUDIO.

I see people repeatedly make the mistake of referencing a very low liquidity prediction market and using it to make a nontrivial point. Usually the implication when a market is cited is that it's number should be taken somewhat seriously, that it's giving us a highly informed probability. Sometimes a market is used to analyze some event that recently occurred; reasoning here looks like "the market on outcome O was trading at X%, then event E happened and the market quickly moved to Y%, thus event E made O less/more likely." Who do I see make this mistake? Rationalists, both casually and gasp in blog posts. Scott Alexander and Zvi (and I really appreciate their work, seriously!) are guilty of this. I'll give a recent example from each of them. From Scott's Mantic Monday post on March 2: Having Your Own Government Try To Destroy You Is (At Least Temporarily) Good For Business On Friday, the Pentagon declared AI company Anthropic a “supply chain risk”, a designation never before given to an American firm. This unprecedented move was seen as an attempt to punish, maybe destroy the company. How effective was it? Anthropic isn’t publicly traded, so we [...] --- First published: March 16th, 2026 Source: https://www.lesswrong.com/posts/SrtoF6PcbHpzcT82T/psa-predictions-markets-often-have-very-low-liquidity-be --- Narrated by TYPE III AUDIO. ---Images from the article:Apple Podcasts and Spotify do not show images in the episode description. Try Pocket Casts, or another podcast app.

AICRAFT: DARPA-Funded AI Alignment Researchers — Applications Open TL;DR: We hypothesize that most alignment researchers have more ideas than they have engineering bandwidth to test. AICRAFT is a DARPA-funded project that pairs researchers with a fully managed professional engineering team for two-week pilot sprints, designed specifically for high-risk ideas that might otherwise go untested. We will select 6 applicants and execute a 2 week pilot with each, the most promising pilot may be given a 3 month extension. This is the first MVP for engaging DARPA directly with the alignment community to our knowledge, and if successful can catalyze government scale investment in alignment R&D. Apply here. Applications close March 27, 2026 at 11 PM PST. What is AICRAFT? AICRAFT (Artificial Intelligence Control Research Amplification & Framework for Talent) is a DARPA-funded seedling project executed by AE Studio. The premise is straightforward: we hypothesize that alignment research could progress faster if the best researchers had more leverage. We believe that researchers currently are bottlenecked on either execution (i.e. they are doing the hands-on experiments themselves) or management (i.e. they are managing teams that are executing the work). Management is higher leverage but what if we could push that much [...] ---Outline:(00:15) AICRAFT: DARPA-Funded AI Alignment Researchers -- Applications Open(01:08) What is AICRAFT?(02:49) The Bigger Picture(03:56) Who should apply?(04:26) How it works(05:21) The application(06:11) FAQ --- First published: March 16th, 2026 Source: https://www.lesswrong.com/posts/nmMdtZveC38atLnDm/aicraft-darpa-funded-ai-alignment-researchers-applications --- Narrated by TYPE III AUDIO.

I am monitoring surveillance camera V84A. A tall man is walking towards me. He is roughly twenty-five. <faceprint> His name is Damion Prescott. He has a room booked for a whole month. His facial symmetry scores show he is in the 99th percentile. This is in accordance with my holistic impression. <search> School records show both truancy and perfect grades, suggesting high intelligence and disagreeableness. Searching social media. <search>. No record of modeling or acting experience, fame. I will assign him to our tier C high-value client list, based solely on his facial symmetry score and wealth. Reminder to recommend seating him in a high-visibility table, should he be heading to the restaurant. <search> I found a forum post mentioning him on swipeshare.com. Several women are sharing pictures, having seen him on a dating app. I recall Hinge uses highly attractive profiles to entice new users. They appear to be using Damion Prescott's profile heavily in this capacity. The women on the site are memeing about him. They are wondering why almost none of them have matched, apparently this is rare even for the most attractive men. Only one appears to have gone on a date with him. She [...] --- First published: March 16th, 2026 Source: https://www.lesswrong.com/posts/LTKfRovaJ6jcwDJia/customer-satisfaction-opportunities-1 --- Narrated by TYPE III AUDIO.

Models that appear aligned under black-box evaluation may conceal substantial latent misalignment beneath their observable behavior. Let's say you downloaded a language model from Huggingface. You do all the blackbox evaluation for the safety/alignment, and you are convinced that the model is safe/aligned. But how badly can things go after you update the model? Our recent work shows, both theoretically and empirically, that a language model (or more generally, a neural network) can appear perfectly aligned under black-box evaluation but become arbitrarily misaligned after just a single gradient step on an update set. Strikingly, this observation can happen under any definition of blackbox alignment and for any update set (benign or adversarial). In this post, I will deep dive into this observation and talk about its implications. Theory: Same Forward Computation, Different Backward Computation LLMs or NNs in general are overparameterized. This overparameterization can lead to an interesting case: 2 differently parameterized models can have the exact forward pass. Think about a simple example: the two-layer linear model and the model . Both models output the input x directly, but backward computations are totally different. Now consider a model that is perfectly aligned under blackbox evaluation, i.e. [...] ---Outline:(01:07) Theory: Same Forward Computation, Different Backward Computation(03:18) Hair-Trigger Aligned LLMs(05:44) Whats Next? --- First published: March 14th, 2026 Source: https://www.lesswrong.com/posts/uSgw9muqRZpjpxKDA/llm-misalignment-can-be-one-gradient-step-away-and-blackbox-1 --- Narrated by TYPE III AUDIO. ---Images from the article:Apple Podcasts and Spotify do not show images in the episode description. Try Pocket Casts, or another podcast app.

Previously: Is GDP a Kind of Factory? There is a word, "convergence," which economists use when they want to say that poor countries are becoming less poor relative to rich ones. There is a phrase, "the resource curse," for the tendency of countries with valuable natural resources to stay poor despite their resources. There is a phrase, "Dutch disease," for the way that selling one commodity too profitably can destroy the ability to sell other things. When an economist says "Dutch disease," they are choosing not to say "Chinese industrial policy combined with structural adjustment conditionality." When they say "the resource curse," they are choosing not to say "extraction concessions negotiated under debt pressure, with domestic officials whose personal interests had already been oriented toward the extraction rather than toward their own population, in conditions created by international creditors who collectively benefited from those terms." When they say "convergence," they are choosing not to say "a temporary windfall from China's industrial buildout, recorded in a measure that cannot distinguish liquidation from accumulation, in countries whose productive capacity was simultaneously being eroded by the same process that temporarily raised their GDP." These words name phenomena while drawing [...] ---Outline:(01:44) Dutch Disease(04:01) The Restructuring of Interests(13:25) Compradorization: The Separation of Interest from Duty(15:50) Reflexive Compradorization: The Prodigal Son(19:24) Construals of Corruption: Fawkes or Villiers?(21:45) Development Consulting: a Case Study(22:44) The Instruments and the Flinch(22:48) The Roles(25:55) The Pervert(26:42) The Hysteric(27:34) The Neurotic(30:22) The Bargain(33:10) Basilisk(34:56) Punctuated Equilibrium(36:15) Outside the Asylum(37:50) What Does This Have to Do with Solow Convergence? The original text contained 4 footnotes which were omitted from this narration. --- First published: March 16th, 2026 Source: https://www.lesswrong.com/posts/8P8bLbNHvC8cHXsBs/compradorization --- Narrated by TYPE III AUDIO.