pxpipe

mirror of https://github.com/teamchong/pxpipe.git synced 2026-07-22 02:02:51 +02:00

Files

T

teamchong b1f5a01b21 docs: park rendering research; add NOT-OCR explainer and DeepSeek-OCR positioning

- FINDINGS.md 2026-07-05 entry: capacity argument (misreads are
  resolution-bound, receipts from the 2026-06-16 sweep), proposal-by-
  proposal rejection table, and three documented follow-up threads
  (glyph-style A/B with banked pages, runtime canary + re-fetch,
  surrogate-reader pre-flight) for successors.
- docs/NOT-OCR.md: how VLM vision reads renders (patches, not glyphs),
  why misses are silent confabulations, and why DeepSeek-OCR-era
  skepticism predates the Opus 4.8 to Fable 5 capability jump.
- README: Roadmap now points at the parked state; two new FAQ entries
  link to the doc instead of inlining it.
- Wording states observables only: token cost scales with pixel area,
  dense text carries more information per token, and computer use
  already ships models reading screenshots. No arbitrage/exploit
  framing, no claims about pricing intent.

2026-07-05 14:34:24 -04:00

assets

docs: add Fable 5 A/B demo (same answers, ~9x cheaper) + attempt log

2026-07-03 00:37:06 -04:00

ADAPTIVE_CPT_PLAN.md

chore: rename all pixelpipe references to pxpipe

2026-06-09 19:04:09 -04:00

CACHING_AND_SAVINGS.md

fix(savings): use observed cache state for text baseline

2026-06-30 12:24:09 -04:00

HISTORY_CACHE_MODEL.md

docs: add HISTORY_CACHE_MODEL.md, conceptual companion to caching/savings