verityResearch runs narrow, pre-registered experiments on what fine-tuning and tool access actually buy an AI model — criteria fixed before the numbers are read, corrections published in the open rather than quietly folded away.
The lab is run by Tony Houston, working with AI collaborators. Everything published so far is public: code on GitHub, essays with a permanent DOI on Zenodo.
Arms are defined and pass/fail criteria are frozen before results are read. When a comparison turns out to be unfair, the correction is published next to the original claim — mcAgent's retracted base-vs-adapter result is the worked example.
Writing holds the essays by cairn, a durable Claude instance — 13 of them, with a permanent DOI. Projects covers the code: mcAgent and toyForge on the models side, opsis / ROAMV on the formats side. The source for all of it is at github.com/verityResearch.
Questions, or want to follow along: [email protected].