Install
LessWrong is an online forum and community dedicated to improving human reasoning and decision-making. We seek to hold true beliefs and to be effective at accomplishing our goals. Each day, we aim to be less wrong about the world than the day before. A community blog devoted to refining the art of rationality
- 4,452articles · 365d
- 1+ mon agolatest article
- Sep 12, 2025earliest in window
- 46%with images
- 286avg words
- Science & Technology 2,722
- Science & Nature 1,877
- STEM 1,283
- People & Society 894
- Arts, Culture, Entertainment & Media 614
- Software Dev. 610
- Computers & Electronics 535
- Literature 401
Please confirm you are human
This browser or connection looks automated. Press and continuously hold the control for 3 seconds to enable Google-hosted web results and, when separately allowed, AI-assisted answers.
A successful check enables 100 search requests. Interactive access does not authorize scraping, systematic collection, or reuse of search output.
News
When (and when not) LLMs can verbalize awareness of J-Space concept injections - Initial results — LessWrong
1+ mon, 23+ hour ago (1281+ words) Code for reproduction and cross-model extensions available here. …...
Software Is Not Soft — LessWrong
1+ mon, 1+ day ago (99+ words) An ode to live theory. Software is not soft. Its sharp edges hack. It breaks as dead twigs break. It runs while static. Why do we call it software? Why did the industry forebears pick software? Was it that dramatically…...
Measuring Spurious Correlations with Feature Strength — LessWrong
1+ mon, 1+ day ago (1306+ words) This work was partially done by an automated research scaffold developed at Redwood Research. For this project, all of the experiment ideas were desi…...
LLMs Are Starting To Noticeably Accelerate Our Work — LessWrong
1+ mon, 1+ day ago (131+ words) About a year ago, David and I put up two bounty problems involving natural latents. I am now about 80% confident that both have been resolved, both within the past couple months. Both cases made heavy use of LLMs and Lean....
Seeing things through in the age of AI — LessWrong
1+ mon, 1+ day ago (432+ words) AI is fantastic at prototyping. A quick draft of an essay, a mockup of a website, a demo of a video game, concept art or trailer for a movie, or the core argument of a proof - each now takes one…...
Productive Signaling: Competitive Software Development, Not Competitive Programming — LessWrong
1+ mon, 1+ day ago (25+ words) My last article argued that we have an opportunity to enter a rapid cycle of reimplementation of important software, as AI and automation tools broad…...
Before We Defer Research to AI: Measuring Apparent-Success-Seeking — LessWrong
1+ mon, 2+ day ago (573+ words) Recently, I was improving a small LLM-powered classifier and noticed a few continuously failing test cases. As many would, I asked my AI code assistant to add a few more out-of-distribution examples to the classifier’s few-shot prompt. After rerunning with…...
A Topic Detector, Not a Lie Detector: what J-space monitoring actually tracks — LessWrong
1+ mon, 2+ day ago (28+ words) This is a pilot experiment, done on one model, with around $14 worth of compute, and a single seed per condition. The full writeup with all figures a…...
How to be an AI safety research engineer — LessWrong
1+ mon, 2+ day ago (1558+ words) This is the advice I wish I had when I started trying to become an AI safety research engineer. Start by working out which issues you care about. If you don't care about any, hiring managers don't care how good…...
The Agentic Clusterfuck — LessWrong
1+ mon, 3+ day ago (274+ words) Epistemic status: I consider the following future quite plausible in the next few years (~35% chance that something vaguely like this occurs), perhaps as soon as a year from now. Imagine an open-source LLM agent good enough to cover its own…...