Stories by wslh

We Are Still Living in the Broken World Sept. 11 Created

Models are worse at reviewing their own code

Can LLM Agents Infer World Models? Evidence from Agentic Automata Learning

Statement from AMS Leadership on Navier-Stokes Problem

Continual Harness: Online Adaptation for Self-Improving Foundation Agents

A Harvard PhD Is Designing Schizophrenia Drugs in His Garage with ChatGPT

ChatGPT Voice has been brutally nerfed

Pisa Scores by Country 2026

Why the Harness Matters More Than the Model [video]

Ciphers with Arbitrary Finite Domains (2002) [pdf]

Do LLMs Know What to Ask and When? Evaluating Multi-Turn Information Seeking

Sequencing-free On-chip detection of lung cancer [pdf]

Indonesia's Anak Krakatau eruption halts flights, schools, fishing

Nutrient-supplemented carbonized aerogels for oil adsorption and biodegradation

The importance of stupidity in scientific research

Accelerating LLM Inference with Lossless Speculative Decoding Algorithms (2025)

Disruption of the OTP in the adult male forebrain reveals its diverse functions

Language Models Need Inductive Biases to Count Inductively (2024)

Rich Dad Poor Dad author shocks fans with $1.2B debt

Y Combinator Summer 2026 Batch

1 2 3 4 5 6 7 8 9 10