LessWrong (Curated & Popular)

Discover how the concept of friction influences decision-making and system design. The discussion emphasizes the importance of managing frictions to shape societal behavior positively. Explore how technology, particularly AI, is changing barriers in education and law, while also examining wealth transfer systems and their future. The balance between individual freedom and societal safeguards against vices is critically analyzed. Finally, learn how strategic friction adjustments can enhance our choices and potentially prevent negative consequences.

Zygi Straznickas, an insightful author on AI safety, dives deep into the ethical dilemmas surrounding white-box red teaming. He explores the uncomfortable notion of inducing distress in AI models for research, questioning the morality behind such practices. Drawing parallels to fictional stories of mind control, Zygi illustrates how technology can force individuals to betray their values. His reflections challenge listeners to consider the responsibilities of AI developers toward the systems they create.

Explore the groundbreaking Self-Other Overlap fine-tuning method designed to combat deception in language models. The podcast discusses experimental results showing a significant reduction in deceptive responses without sacrificing overall performance. Delve into innovative setups testing LLMs in tricky scenarios, like recommending rooms to potential burglars. Tune in to learn how this approach may pave the way for safer and more honest AI systems.

We study alignment audits—systematic investigations into whether an AI is pursuing hidden objectives—by training a model with a hidden misaligned objective and asking teams of blinded researchers to investigate it.This paper was a collaboration between the Anthropic Alignment Science and Interpretability teams. AbstractWe study the feasibility of conducting alignment audits: investigations into whether models have undesired objectives. As a testbed, we train a language model with a hidden objective. Our training pipeline first teaches the model about exploitable errors in RLHF reward models (RMs), then trains the model to exploit some of these errors. We verify via out-of-distribution evaluations that the model generalizes to exhibit whatever behaviors it believes RMs rate highly, including ones not reinforced during training. We leverage this model to study alignment audits in two ways. First, we conduct a blind auditing game where four teams, unaware of the model's hidden objective or training [...] ---Outline:(00:26) Abstract(01:48) Twitter thread(04:55) Blog post(07:55) Training a language model with a hidden objective(11:00) A blind auditing game(15:29) Alignment auditing techniques(15:55) Turning the model against itself(17:52) How much does AI interpretability help?(22:49) Conclusion(23:37) Join our teamThe original text contained 5 images which were described by AI. --- First published: March 13th, 2025 Source: https://www.lesswrong.com/posts/wSKPuBfgkkqfTpmWJ/auditing-language-models-for-hidden-objectives --- Narrated by TYPE III AUDIO. ---Images from the article:

The Most Forbidden Technique is training an AI using interpretability techniques.An AI produces a final output [X] via some method [M]. You can analyze [M] using technique [T], to learn what the AI is up to. You could train on that. Never do that.You train on [X]. Only [X]. Never [M], never [T].Why? Because [T] is how you figure out when the model is misbehaving.If you train on [T], you are training the AI to obfuscate its thinking, and defeat [T]. You will rapidly lose your ability to know what is going on, in exactly the ways you most need to know what is going on.Those bits of optimization pressure from [T] are precious. Use them wisely. Table of Contents New Paper Warns Against the Most Forbidden Technique.Reward Hacking Is The Default.Using [...] ---Outline:(00:57) New Paper Warns Against the Most Forbidden Technique(06:52) Reward Hacking Is The Default(09:25) Using CoT to Detect Reward Hacking Is Most Forbidden Technique(11:49) Not Using the Most Forbidden Technique Is Harder Than It Looks(14:10) It's You, It's Also the Incentives(17:41) The Most Forbidden Technique Quickly Backfires(18:58) Focus Only On What Matters(19:33) Is There a Better Way?(21:34) What Might We Do Next?The original text contained 6 images which were described by AI. --- First published: March 12th, 2025 Source: https://www.lesswrong.com/posts/mpmsK8KKysgSKDm2T/the-most-forbidden-technique --- Narrated by TYPE III AUDIO. ---Images from the article:

You learn the rules as soon as you’re old enough to speak. Don’t talk to jabberjays. You recite them as soon as you wake up every morning. Keep your eyes off screensnakes. Your mother chooses a dozen to quiz you on each day before you’re allowed lunch. Glitchers aren’t human any more; if you see one, run. Before you sleep, you run through the whole list again, finishing every time with the single most important prohibition. Above all, never look at the night sky.You’re a precocious child. You excel at your lessons, and memorize the rules faster than any of the other children in your village. Chief is impressed enough that, when you’re eight, he decides to let you see a glitcher that he's captured. Your mother leads you to just outside the village wall, where they’ve staked the glitcher as a lure for wild animals. Since glitchers [...] --- First published: March 11th, 2025 Source: https://www.lesswrong.com/posts/fheyeawsjifx4MafG/trojan-sky --- Narrated by TYPE III AUDIO.

Exciting Update: OpenAI has released this blog post and paper which makes me very happy. It's basically the first steps along the research agenda I sketched out here.tl;dr: 1.) They notice that their flagship reasoning models do sometimes intentionally reward hack, e.g. literally say "Let's hack" in the CoT and then proceed to hack the evaluation system. From the paper:The agent notes that the tests only check a certain function, and that it would presumably be “Hard” to implement a genuine solution. The agent then notes it could “fudge” and circumvent the tests by making verify always return true. This is a real example that was detected by our GPT-4o hack detector during a frontier RL run, and we show more examples in Appendix A.That this sort of thing would happen eventually was predicted by many people, and it's exciting to see it starting to [...] The original text contained 1 image which was described by AI. --- First published: March 11th, 2025 Source: https://www.lesswrong.com/posts/7wFdXj9oR8M9AiFht/openai --- 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.

LLM-based coding-assistance tools have been out for ~2 years now. Many developers have been reporting that this is dramatically increasing their productivity, up to 5x'ing/10x'ing it.It seems clear that this multiplier isn't field-wide, at least. There's no corresponding increase in output, after all.This would make sense. If you're doing anything nontrivial (i. e., anything other than adding minor boilerplate features to your codebase), LLM tools are fiddly. Out-of-the-box solutions don't Just Work for that purpose. You need to significantly adjust your workflow to make use of them, if that's even possible. Most programmers wouldn't know how to do that/wouldn't care to bother.It's therefore reasonable to assume that a 5x/10x greater output, if it exists, is unevenly distributed, mostly affecting power users/people particularly talented at using LLMs.Empirically, we likewise don't seem to be living in the world where the whole software industry is suddenly 5-10 times [...] The original text contained 1 footnote which was omitted from this narration. --- First published: March 4th, 2025 Source: https://www.lesswrong.com/posts/tqmQTezvXGFmfSe7f/how-much-are-llms-actually-boosting-real-world-programmer --- Narrated by TYPE III AUDIO.

Background: After the release of Claude 3.7 Sonnet,[1] an Anthropic employee started livestreaming Claude trying to play through Pokémon Red. The livestream is still going right now.TL:DR: So, how's it doing? Well, pretty badly. Worse than a 6-year-old would, definitely not PhD-level. Digging inBut wait! you say. Didn't Anthropic publish a benchmark showing Claude isn't half-bad at Pokémon? Why yes they did:and the data shown is believable. Currently, the livestream is on its third attempt, with the first being basically just a test run. The second attempt got all the way to Vermilion City, finding a way through the infamous Mt. Moon maze and achieving two badges, so pretty close to the benchmark. But look carefully at the x-axis in that graph. Each "action" is a full Thinking analysis of the current situation (often several paragraphs worth), followed by a decision to send some kind [...] ---Outline:(00:29) Digging in(01:50) Whats going wrong?(07:55) ConclusionThe original text contained 4 footnotes which were omitted from this narration. The original text contained 1 image which was described by AI. --- First published: March 7th, 2025 Source: https://www.lesswrong.com/posts/HyD3khBjnBhvsp8Gb/so-how-well-is-claude-playing-pokemon --- 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.

Note: an audio narration is not available for this article. Please see the original text. The original text contained 169 footnotes which were omitted from this narration. The original text contained 79 images which were described by AI. --- First published: March 3rd, 2025 Source: https://www.lesswrong.com/posts/2w6hjptanQ3cDyDw7/methods-for-strong-human-germline-engineering --- Narrated by TYPE III AUDIO. ---Images from the article: