Acta Machina

Extending Anthropic’s Agent Workflows with Recursive Planning

Experiments in Constrained LLM Decoding

AIMO Progress Prize 1

Generative AI Interfaces

Bletchley Park’s Legacy in Code

Adapting Gymnasium to Find DeepRacer Racing Lines

Driving Trajectory Extraction from Image Sequences

Handwritten Equation Recognition with Transformers

Deriving Blackjack’s Basic Strategy using Reinforcement Learning

Revisiting the Algorithm that Changed Horse Race Betting