Stories by bearseascape

Model Spec Midtraining: Improving How Alignment Training Generalizes

Following the Text Gradient at Scale (2025)

Transformers Are Inherently Succinct (2025)

Slople – Can you tell real ML papers from AI-generated ones?

Benchmarking Culture

Why one small American town won't stop stoning its residents to death

The most complex model we understand [video]

Weird Generalization and Inductive Backdoors: New Ways to Corrupt LLMs

MooseAgent: A LLM Based Multi-Agent Framework for Automating Moose Simulation

Automated Researchers Can Subtly Sandbag

Auditing Language Models for Hidden Objectives

Policy for LLM Writing on LessWrong

Towards Understanding Distilled Reasoning Models: A Representational Approach

Transformers Learn to Implement Multistep Gradient Descent with Chain of Thought

(Mis)Fitting: A Survey of Scaling Laws

Resurrecting saturated LLM benchmarks with adversarial encoding

Deep Double Descent: Where Bigger Models and More Data Hurt

Value-Based Deep RL Scales Predictably