Building an agent harness from scratch to pass Ian Goodfellow's intelligence test
What was once considered a test of "real AI" - now built entirely in a single blog post.
HarnessDesign
-
-
Harness Engineering Anatomy, Architecture, and Evolution of Coding Agents
A source-code comparison of eleven agent harnesses and the seven parts they have in common.
-
An Empirical Study of Harness Design for Coding Agents
An ablation of planning, tools and context management configurations for coding agents.
-
Heavy Thinking: A Test-Time Scaling Pattern for Hard Problems
Now we have GPT Pro at home