LessWrong (Curated & Popular)

"Greater good arguments in AI safety" by Dean Valentine

Back in the before-time of the 2010s, when EA was still known mostly for funding health efforts in the developing world, there were many baskets of criticism floating aro

"Wah wah wah wah do more AI R&D" by TsviBT

Ice cream There's a particular kind of listening that kids (and adults) sometimes do. Daddy is saying stuff—his mouth is moving and making noise—and he's talk

"Why I’m becoming a professor in AI safety in Beijing" by Buddenbroke

Cross-posted from Sören Mindermann's substack (I am not Sören). Should be of general interest to the LW community. Next month, I am moving to Beijing and joining

"A brief(ish) introduction to LM psychology" by Raymond Douglas, Jan_Kulveit

Why LM Psychology? One of the great ironies of modern language models is that we create them, we know exactly what computations constitute them, and yet we do not reall

"There Will Be Hells" by Stephen Martin

As our understanding of mechanistic interpretability and steering techniques increase, for both LLMs and uploaded connectomes, there is a corresponding "hellish capabilit

[Linkpost] "huggingface.wtf, an accessible but complete explanation" by Raemon

This is a link post. Announcing www.huggingface.wtf, a site that explains: "Hugging Face. Wtf?" I wrote the most accessible-but-complete explanation I could. Along the

"Gradient Routing Localizes and Removes Unintended Behaviors in RL" by shawnghu, Jake Ward, ariaw, Nathan Hu, Bryce Woodworth, TurnTrout, cloud

Authors: Shawn Hu*, Jake Ward*, Aria Wong, Nathan Hu, Bryce Woodworth, Alexander Matt Turner, Alex Cloud (*Equal contribution, randomly ordered) tl;dr. During training,

[Linkpost] "Capital Ownership Will Make You Go Crazy First" by Jan_Kulveit

This is a link post. People worried about a “permanent underclass” often assume that owning capital will protect them from disempowerment, or at least that they will be d

"I Did This Without Your Knowledge" by joec

It's fortunate that I was the first one to wake up on 8/1. The past week had been one where sleep was rare. The next year loomed large — I was dreading college appli

"Neural networks are not already clean" by leogao

What would it take to get assurance that we have actually explained a neuron? Certainly, it would be a good sign if neuron activations looked like they had a consistent p

"GLM-5.3 Sometimes Considers How Train-Time Actions Shape Future Behavior" by Axel Højmark, Ezra Newman

Authors: Axel Højmark*, Ezra Newman* (*Equal contribution) While reviewing transcripts from standard behavioral evaluations of GLM-5.3, we noticed that the model occasi

"A Chinese Perspective on “On Social Reality in China”" by Dusty

I think “On Social Reality in China” makes many accurate observations, but I find the comparison fundamentally uneven. There are already many interesting comments there,

"Your prompt… plus everything you’ve ever (publicly) written" by kromem

TL;DR: Increasingly when you interact with frontier models, your prompt doesn't only contain the words on the page, but also a lot of what you've ever publicly

"Linkpost: Neural Networks Are Already Clean" by Yair Halberstadt

This is an extremely lengthy post by Nick Cammarata. Author's summary on twitter: interpretability might be the most important scientific problem in the world ri

"Personas in a Pre-Internet Language Model" by David Africa

David Africa & Nick Levine TLDR We ran several persona experiments on Talkie, a 13B model trained only on English text from before 1931. We ran them alongside its mod

"Not Deciphering The Voynich Manuscriptraft" by rba

The Piltdown man was the most successful artifactual hoax of all time. The relevant skull was a chimeric melange of orangutan and human bone fragments from several indivi

"Quantity vs quality in pottery is a lie" by becausecurious

Epistemic status: I traced one famous anecdote to its printed source and to both coauthors' own accounts of where it came from. Confident it was never a study. No cl

"Labs’ current alignment plans seem terrible" by Daniel Tan, draganover, nicole x

Tl;dr: The frontier AI companies’ implicit alignment plans center on rushing towards RSI with something like current models. This plan is (at best) contentious, and many

"Research Lessons I Learned at MATS & Redwood" by Jo Jiao

Good empirical safety research is heavily bottlenecked on thinking more clearly. This post shares a few frames and tips I found useful, illustrated with concrete examples

"You Heard of “Bayesians Don’t Predictably Update” Because of Robin Hanson" by Eliezer Yudkowsky

Robin Hanson didn't invent the idea of a martingale process. The lilim say that Ville in 1939 gave the term its mathematical meaning and Doob turned it into the mode