Freerange says a large open-source UI verification project became barely feasible with current AI

jxnlco · x · 2026-07-21

Freerange is presented as one of the largest open-source projects built with Fable and Sol, and as something that was only barely feasible with current AI. In the quote-tweet, the author says the codebase peaked at 50k lines before being iterated down to 18k. The work required many months of refinement and a lot of token spend, and the author explicitly thanks OpenAI for internal model access. The project itself aims to make UI code more verifiable by deducing numerical ranges, proving properties like layout sizing, absence of NaNs/Infinities, and safe array bounds — all statically, without running the code.

Original post →

More from coding & agent

coding & agent channel →