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.
More from coding & agent
- Matt Pocock says every new codebase turns legacy within days — mattpocockuk · 2026-07-21
- Ramp says its model router cuts LLM costs by 30% by picking the cheapest good model — rohanpaul_ai · 2026-07-21
- Meta and Unity link AI workflows to Quest development across setup, input and validation — Vjeux · 2026-07-21
- AI Engineer World’s Fair spotlights Kids Day with 87 children learning to code — steveonjava · 2026-07-21
- Looking Glass adds persistent coding sessions that can schedule their own next turns — teleport66 · 2026-07-21
- Kimi K3 looks stronger and about 5× cheaper on a frontend dashboard task — OwariDa · 2026-07-21