Technique

Chain of Thought

Prompting a model to reason step by step, which improves accuracy on complex tasks.

A full explainer for this concept is being written. In the meantime, here's what's in the news.

In the news

The Communication Bottleneck: A Round-Trip Study of Tree-Structured Expression Serialization in Language Models

Apple ML Research · Sep 29, 2026

🔬Bio-security is an AI Arms Race - Eric Nguyen (CEO, Radical Numerics)

Latent Space · Sep 23, 2026

What’s neuralese and why is everyone so concerned about it?

Transformer · Sep 3, 2026

Stealing Reasoning Traces from Proprietary LLM APIs

Simon Willison · Aug 11, 2026

Arbitrage: Efficient Reasoning via Advantage-Aware Speculation

Apple ML Research · Aug 7, 2026

On Robustness and Chain-of-Thought Consistency of RL-Finetuned VLMs

Apple ML Research · Jul 2, 2026