20:56
2026-09-17
dev.to
ai-tools
I taught a 27B model to write Forge apps. As far as I can find, nobody had done that before
A developer at LeanZero fine-tuned Qwen3-27B to write Atlassian Forge apps, raising identifier accuracy from 15% to 69% and Forge manifests passing Atlassian's validator from 0 of 25 to 14 of 25, with…