pdf-inspector retest: 947 pages in 6.9 min, but 66.6% of numeric values missing from markdown
Ubunta · x · 2026-09-05
Ubunta corrects their earlier pdf-inspector criticism: the 275s timing was a bug in their own method—pages= filters run after whole-document work (pages=1 and pages=8 both 278s). Real numbers: pdf-inspector processes a 947-page clinical listing in 6.9 min vs their pipeline's 6.2 min—competitive. The real blocker: 66.6% of numeric values are missing from the markdown and there's no cell geometry (page/table/row/column/bounding box), which matters for citing numbers in regulated documents.
More from coding & agent
- GPT-6 Astra builds a procedural three.js game under 2MB, then remakes it in Blender — gabrielchua · 2026-09-05
- OpenAI brings ChatGPT and Codex into UPenn drug discovery workflows — AllThingsApx · 2026-09-05
- Codex /fast mode runs at 2x speed and stays within subscription, unlike Claude's paid extra usage — rudrank · 2026-09-05
- ChatGPT Workspace 5-hour limit mid-agent-run wipes uncommitted code, dev demands fix — cneuralnetwork · 2026-09-05
- Astra costs ~$1.49/M tokens for this dev's coding — but is it good enough to be the default? — notchillatall · 2026-09-05
- HeroUI launches Agents: embed a context-aware agent in your product — ycombinator · 2026-09-05