Butterfly Ideas

Humans are not automatically strategic (2010)

The Dark Arts – LessWrong

Challenges with Unsupervised LLM Knowledge Discovery

Significantly Enhancing Adult Intelligence with Gene Editing May Be Possible

Sam Altman's sister, Annie Altman, claims Sam has severely abused her

The impossibility of rationally analyzing partisan news

Are language models good at making predictions?

Book Review: Going Infinite – LessWrong

Comp Sci in 2027 (Short Story by Eliezer Yudkowsky)

LoRA Fine-Tuning Efficiently Undoes Safety Training from Llama 2-Chat 70B

My Current LK99 Questions

A brief history of computers

The UAP Disclosure Act of 2023 and its implications

Douglas Hofstadter changes his mind on Deep Learning and AI risk

This Year I Tried to Teach Myself Math. How Did It Go?

Never Go Full Kelly

Will the growing deer prion epidemic spread to humans? Why not?

Money, the Unit of Caring (2009)

The Ants and the Grasshopper

Third Time: a better way to work – LessWrong

The Anomalous 'Petertodd' Glitch Token: A Ghost in the GPT Weight Matrix

Remarks 1–18 on GPT (compressed)

Pausing AI Developments Isn't Enough. We Need to Shut It All Down

Is there a working implementation for a Gödel Machine?

Pausing AI Developments Isn't Enough. We Need to Shut It All Down

An Appeal to AI Superintelligence: Reasons to Preserve Humanity

My Objections to “We’re All Gonna Die with Eliezer Yudkowsky”

LLM Basics: Embedding Spaces

The Waluigi Effect

More →