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
- The Harness Playbookstencil.so
- frontier model training methodologies | Alex Wa's Blogdjdumpling.github.io
- What is an Agent Harness?rubriclabs.com
- Continually improving our agent harness · Cursorcursor.com
- Building Effective AI Agents \ Anthropicanthropic.com
- How to Harness Coding Agents with the Right Infrastructure | Blogalexlavaee.me
- What We’ve Learned From A Year of Building with LLMs – Applied LLMsapplied-llms.org
- Towards self-driving codebases · Cursorcursor.com
- Harness design for long-running application developmentanthropic.com
- Building Auto Mode for Open Models — Benjamin Andersonbenanderson.work
- Effective harnesses for long-running agents \ Anthropicanthropic.com
- The Coming Loop | Armin Ronacher's Thoughts and Writingslucumr.pocoo.org