Two-pass doc pattern: 12,013 SEC pages skimmed in 32s, VLM OCR on just 2
dl_weekly · x · 2026-09-21
DL Weekly highlights a two-pass document processing pattern: a cheap first pass skimmed 84 SEC filings (12,013 pages) in 32 seconds, then expensive VLM OCR ran on only two selected pages.
The core idea is using a low-cost scan to locate the few pages that need deep visual understanding, minimizing costly vision model calls while keeping speed.
More from coding & agent
- LlamaIndex launches DocJev: OSS doc classification 6x faster than gpt-5.6-luna — multiply_matrix · 2026-09-21
- Ante v0.2.0 ships a stream protocol decoupling agent engines from interfaces — JaynitMakwana · 2026-09-21
- Rethinking classifiers: conversation+tool templates as special cases of inference-time specs — austinvhuang · 2026-09-21
- Analyst predicts Meta will pay Amazon for agent access, spawning a new agent business model — signulll · 2026-09-21
- Arena: coding-agent harnesses show up to 5x cost differences at similar success rates — thione · 2026-09-21
- Recap: Anthropic merged Claude chat and Cowork, redesigned Claude Code Projects — thione · 2026-09-21