LessWrong (30+ Karma)

This is a five-week interim report for a MATS 8.0 project supervised by Marius Hobbhahn. Produced as part of the ML Alignment & Theory Scholars Program - Summer 2025 Cohort.

Executive Summary

• Our g…

There's now over 100 comments on “My Empathy Is Rarely Kind”, and the consensus response is roughly “John, that's not what empathy is”.

So, first things first: I agree. I was using the wrong words f…

TL;DR

I believe that:

• Almost all LLM-centric safety research will not provide any significant safety value with regards to existential or civilisation-scale risks.
• The capabilities-related forecast…

Table of Contents

1. College Applications.
2. The College Application Essay (Is) From Hell.
3. Don’t Guess The Teacher's Password, Ask For It Explicitly.
4. A Dime a Dozen.
5. Treat Admissions Essays Like…

Produced as part of MATS 8.0 under the mentorship of Alex Turner and Alex Cloud. This research note overviews some early results which we are looking for feedback on.

TL;DR: We train language model…

SHANGHAI, July 26 (Reuters) - China said on Saturday it wanted to create an organisation to foster global cooperation on artificial intelligence, positioning itself as an alternative to the U.S. as …

There's a narrative I hear a lot: if I empathize more, put myself in other peoples’ shoes, try to feel what they’re feeling, see things from their perspective, etc, then I’ll feel kinder toward them…

I’d like to thank my mentors David Duvenaud, Raymond Douglas, David Krueger and Jan Kulveit for providing helpful ideas, comments and discussions. The views expressed in this, and any mistakes, are …

The Tea app is or at least was on fire, rapidly gaining lots of users. This opens up two discussions, one on the game theory and dynamics of Tea, one on its abysmal security.

It's a little too on t…

Since Tom Lehrer passed away recently, I thought I'd honor him by adapting one of his songs to be about a more recent existential risk. Presenting...

"We Will All Go Together When We Go (ASI versio…

Nick Bostrom defines existential risk as

Existential risk – One where an adverse outcome would either annihilate Earth-originating intelligent life or permanently and drastically curtail its poten…

Nick Bostrom defines existential risk as

Existential risk – One where an adverse outcome would either annihilate Earth-originating intelligent life or permanently and drastically curtail its poten…

FutureHouse is a company that builds literature research agents. They tested it on the bio + chem subset of HLE questions, then noticed errors in them.

The post's first paragraph:

Humanity's Last Ex…

Have you ever been endlessly procrastinating on some task, but then once you eventually, finally do it, you realize that it is not half as bad as you thought?

Somehow, many of us keep overestimating…

Both my kids can swim! Yay! 🥂🍾 Some notes about the process:

• The options were group lessons, individual lessons, and parent-is-the-teacher. We have tried all three. Individual lessons were logistic…

Meta: Last year I wrote a retrospective of the first LessOnline. This year, several people told me that they’d read it and found it helpful/interesting/entertaining, so I figure I’ll do it again. It…

Thanks to Jasmina Urdshals, Xavier Poncini, and Justis Mills for comments.

Introduction

At Simplex our mission is to develop a principled science of the representations and emergent behaviors of AI…

Link to our arXiv paper: https://arxiv.org/abs/2507.15886

TL, DR;: We study how to efficiently combine multiple monitors with different performance and cost profiles into a single protocol. When t…

A science-fiction short story exploring how far AI capitalists might go in their quest for (the illusion of) success. Wildly speculative, of course.

?

Thank you, but if you don’t mind, I’d prefer …