Building a harness for open models | writings
parthsareen.com · 3,537 words · saved by 1 readers
What open models expose about context, tools, policy, and the agent loop around them.
A model that “forgot” the task may have been shown mostly stdout. A model that uses the wrong tools may have been given a transcript where compaction rewrote the goal into something vague. And a model that seems “slow” may be running in a harness that adds the current time to the system prompt on every turn, breaking cache reuse. I know that last one a little too well. Most popular agent harnesses were built around closed frontier models. Closed models have huge context windows, a lot of recovery ability, and a pretty generous token budget, so a lot of harness bugs never surface. You can…
saved by
related reading
- Inside Coding Agentsvpromise.github.io
- What is an Agent Harness?rubriclabs.com
- The Harness Playbookstencil.so
- Continually improving our agent harness · Cursorcursor.com
- Building reliable AI agents · parth sareenparthsareen.com
- Inkling: Our Open-Weights Model - Thinking Machines Labthinkingmachines.ai
- [2606.09498] Self-Harness: Harnesses That Improve Themselvesarxiv.org
- Lecture 01. Strong Models Don't Mean Reliable Execution | Learn Harness Engineeringwalkinglabs.github.io
- Bring Your Own Harness to AC2appliedcompute.com
- Building Auto Mode for Open Models — Benjamin Andersonbenanderson.work
- Arjun Virkarjunvirk.com
- [2606.09498] Self-Harness: Harnesses That Improve Themselvesarxiv.org