Two models built a legal PDF text library that works well and stalls at 80 percent
Fable and the AI vibecoded a library improving text extraction from legal PDFs; it works pretty well but is stalled at about 80 percent on design and heuristics, with the models churning.
This only partly worked. Read what happened before you try it.
How it works
- Two models vibecode a library improving text extraction from legal PDFs
- It works pretty well
- Stalls at about 80 percent on design and heuristics
Why it’s worth knowing
The last 20 percent of extraction is where the law hides.
Where it’s from
Summarized from a public post on news.ycombinator.com. See the original ↗