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

Files

T

teamchong b7de47eb3f docs: add Fable 5 A/B demo (same answers, ~9x cheaper) + attempt log

- README: Fable clip as headline demo (Drive link + committed thumb),
  verified numbers from the recording: plain $42.21 / 96% context vs
  pxpipe $4.51; honest caveat on single-reply format compliance
- ATTEMPTS.md: attempt 1 (invalid run, model-switch pitfall) and
  attempt 2 (legibility PASS on fable, format miss documented)
- a.sh/b.sh: prompt fix — numbering starts at filler-000

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

cost-ab

fix(demo): add --no-chrome to both cost-ab arms

2026-07-02 22:24:13 -04:00

effective-context

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

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

README.md

docs(demo): cost-ab + effective-context A/B demos with a model arg

2026-06-17 10:01:33 -04:00

README.md

pxpipe demos

Two demos, two questions, two honest verdicts.

folder	question	status
`cost-ab/`	Does pxpipe cost less on a real task?	~break-even. Compression is real but lands in `cache_read` (cheap at `$`, rumored-free at the subscription cap); session divergence dominates the totals.
`effective-context/`	Does pxpipe stay sharp in a context that overloads the plain column?	unvalidated — modern long-context Claude may not "drown," so run it before claiming a win.

What is validated: in the cost A/B's Rust-rewrite task, both columns ported a whole library to Rust and both passed all 5 tests with the exact expected integers — pxpipe through imaged spec + source. So compression didn't break a precision task. pxpipe's case rests on capability (not breaking real work, and effective context), not on saving tokens.

Shared tooling: ../eval/ab/analyze.mjs reads the two proxy logs (ab-on.jsonl / ab-off.jsonl) and reports the honest cost comparison.