LargeLanguageModels

Language models that manage their own context.

An LLM-judge approach that brings interpretability and actionability to your scores.

The two steps to training modern LLMs.

How LLMs use intermediate reasoning tokens, from chain-of-thought prompting to trained reasoning models, and how this relates to other forms of reasoning.

Optimising computation at the token-level

aka Self-Confidence is All You Need

Using evolutionary algorithms with LLM-coding agents

learn to reason without any human-annotated data.

a parameter that controls how confident Softmax predictions are

Routes LLM tasks to cheaper or more powerful models based on task novelty.