Website profile

lesswrong.com

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

  • 898articles · 90d
  • 1+ mon agolatest article
  • Jun 16, 2026earliest in window
  • 45%with images
  • 172avg words
articles per day
Categories
  • Science & Technology 576
  • Science & Nature 378
  • STEM 268
  • Computers & Electronics 158
  • Software Dev. 153
  • People & Society 143
  • Arts, Culture, Entertainment & Media 126
  • Jobs & Education 77

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.

Hold with a pointer, or hold Space or Enter.

News

lesswrong.com
lesswrong.com > posts > ysztF7doGvEbvTMqN > how-do-neural-networks-regress-cubic-polynomials-apparently

How do neural networks regress cubic polynomials? Apparently, they use a trick invented in Milan 500 years ago — LessWrong

1+ mon, 3+ week ago   (1423+ words) TL;DR: Neural networks can easily learn to regress cubic polynomials of type, but how do they do that? Results show that they internally access a va…...

lesswrong.com
lesswrong.com > posts > BaFbWjFhusjazeSuN > theories-of-deep-learning-1

Theories of Deep Learning — LessWrong

2+ mon, 2+ day ago   (855+ words) NOTE: These are mathematically dense frameworks which either provide a language for formalizing the field itself or aim to explain the observed phenomena. This essay is my personal understanding of the theories, after a lot of back and forth with…...

lesswrong.com
lesswrong.com > posts > 4nZwNPyfoadAxPH98 > natural-language-autoencoders-are-summarizers-but-do-they

Natural Language Autoencoders are summarizers, but do they have to be? — LessWrong

2+ mon, 4+ day ago   (1392+ words) TL;DR: NLAs are an interesting idea. They do reconstruct the activations well, they can kinda audit model organisms for hidden objectives. But there…...

lesswrong.com
lesswrong.com > posts > QR4AgigAopdz9LvQk > power-laws-in-nns-a-possible-mechanism-for-inductive-bias

Power Laws in NNs: A Possible Mechanism for Inductive Bias towards Sparse Representations — LessWrong

2+ mon, 2+ week ago   (875+ words) This post was produced as part of the Iliad Fellowship under the mentorship of Dmitry Vaintrob. …...

lesswrong.com
lesswrong.com > posts > EsiLnZGDHpYoZXGAh > naturally-learned-behaviors-in-deep-mlps-resist-detection-by

Naturally learned behaviors in deep MLPs resist detection by both human and learned algorithms — LessWrong

2+ mon, 3+ week ago   (840+ words) Introduction An ambitious problem in mechanistic interpretability of neural networks is finding an input for a neural network that produces a certain…...

lesswrong.com
lesswrong.com > posts > H8ktAMBv8jQr8JymL > introduction-gaussian-natural-latents

Introduction: Gaussian Natural Latents — LessWrong

2+ mon, 3+ week ago   (22+ words) Short introductory post for my research direction: Gaussian Natural Latents. I explain the motivation and give a preview of the forthcoming results. …...