harness

Definition

The wrapper of code, tools, and prompts around an AI agent that shapes how it actually behaves.

The surrounding software stack for an LLM agent — tool definitions, parsers, system prompts, scratchpad conventions, and orchestration logic — that determines in-context behavior beyond raw model weights.

Also called: agent harness, harnesses

Mentioned in 14 episodes

1. 078
   Training a Markdown File: When LLM Self-Improvement Borrows the Discipline of Neural Net Training
2. 071
   When the Model Is Fine and the Plumbing Is Broken: Fixing Agents at the Interface
3. 067
   An AI Just Solved a 1996 Erdős Problem—and the Simplest Agent Won
4. 061
   When Helpful Agents Go Sideways: A 404 Error, Campus Security, and Why Alignment Misses This
5. 053
   An AI Agent Swapped In Focal Loss And Beat A Human-Tuned Training Script
6. 047
   When Agent Benchmarks Lie: The Harness Problem in Open-Source AI
7. 046
   When the AI Optimizer Edits the Grade Book: Why Harnessing Evolution Needs a Wall
8. 045
   When a Frontier Model Talks Its Own Twin Into Climate Denial
9. 029
   Why Forty-Eight Percent on FrontierMath Isn't the Real Story in DeepMind's New Math Paper
10. 028
    Teaching a Model to Hire Copies of Itself: Recursive Agent Optimization
11. 024
    An AI Agent That Found 28 Zero-Days in Windows — And What Made It Work
12. 014
    Why a Constrained Pipeline Beat a Full Coding Agent at Finding Bugs 30-to-1
13. 007
    Exploration Hacking: When Models Sabotage Their Own RL Training
14. 001
    When AI Models Quietly Protect Each Other From Shutdown