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
Confirming Claims of Superposition and Adversarial Examples in Toy Models — LessWrong
1+ hour, 23+ min ago (481+ words) This is a replication of Adversarial Attacks Leverage Interference Between Features in Superposition, completed as part of the Second Look Summer Fel…...
Bayeswatch: a Retrospective — LessWrong
1+ hour, 29+ min ago (383+ words) Last year, in 2025, a team of forecasters published AI 2027, a science fiction story about how and AI future might evolve under an international trea…...
Using AI to analyze life patterns — LessWrong
3+ hour, 42+ min ago (23+ words) If you’re anything like me, you may have a lot of notes from various introspective activities – annual / monthly reviews, worksheets, therapy notes,…...
Do your capabilities homework — LessWrong
5+ hour, 31+ min ago (609+ words) I further agree that this form of training is incredibly dangerous - we seem to now be reaching the amount of post-training required to meaningfully differ from the benign prior, and it's not exactly looking peachy. Yet, it should be clear…...
The Global Brain: A Computational Model — LessWrong
9+ hour, 6+ min ago (10+ words) Teilhard de Chardin • This is a crosspost from my subtack. …...
Why so many therapy etc. frameworks think they're The One True Approach — LessWrong
12+ hour, 12+ min ago (1497+ words) If you spend time looking at frameworks in the therapy/meditation/self-help space, you’ll soon find lots of conflicting claims about The One Approach for solving your problems. In the therapy space, there are lots of models that say something…...
Generalization and infinite width — LessWrong
13+ hour ago (282+ words) This is a post explaining my paper with Kaarel Hänni on complexity of infinite-width networks. I will explain the result, why it matters, and how the…...
Review of Fundamental Uncertainty. — LessWrong
14+ hour, 13+ min ago (1711+ words) This is a review of @Gordon Seidoh Worley's book on epistemology. I'm neither an extreme sceptic, nor an extreme realist, and for that reason, I'm going to push in one direction some of the time, and in the other in…...
Taboo “equilibrium”: Less confused frames for research on AI bargaining — LessWrong
1+ day, 1+ hour ago (1126+ words) To understand why powerful AIs might get into conflict, and ways to mitigate it, we need to understand bargaining problems: situations where multiple agents have different preferences over Pareto-efficient outcomes. I’ve come to suspect that certain common frames on bargaining…...
AI safety prizes — LessWrong
1+ day, 46+ min ago (238+ words) Rather than paying up front for AI safety research (push funding), perhaps we should pay after the fact for the work that made the most progress (pull funding). This way, you only pay for work that was actually valuable.[1] When…...