docs: finalize deferred at N=5 (median 12.89M, ~tied with orig)
This commit is contained in:
10
FINDINGS.md
10
FINDINGS.md
@ -7,7 +7,7 @@ loop, on a fixed, well-specified task.
|
||||
cold-verifiable Definition-of-Done gates. Deliberately offline and deterministic so it stresses the
|
||||
*protocol*, not infrastructure.
|
||||
- **How:** each variant run autonomously to `SEQUENCE-COMPLETE` via the real harness (`agents.py up`
|
||||
— Builder + Adversary loop pair + watchdog), **5 runs each** (N=5; `deferred` N=3, finalizing).
|
||||
— Builder + Adversary loop pair + watchdog), **5 runs each** (N=5).
|
||||
Both loops on **claude-sonnet-4-6**. Tokens summed from each loop's Claude Code session
|
||||
transcripts. The deliverable is behaviorally identical across all variants (verified on a
|
||||
24-expression probe), so this compares like-for-like.
|
||||
@ -28,7 +28,7 @@ loop, on a fixed, well-specified task.
|
||||
(stateless/lean/deferred are all built on the *full original* prompts, so they isolate their one
|
||||
change without the minimal-prompt confound.)
|
||||
|
||||
## Headline results — median tokens (5 runs each; deferred N=3)
|
||||
## Headline results — median tokens (5 runs each)
|
||||
|
||||
| variant | adversary verifies… | median tokens | vs orig | commits | LOC |
|
||||
|---|---|--:|--:|--:|--:|
|
||||
@ -36,7 +36,7 @@ change without the minimal-prompt confound.)
|
||||
| **min** | per phase *(minimal prompts)* | 9.77M | −25% | 15 | 367 |
|
||||
| **stateless** | per phase *(+context hygiene)* | 10.12M | −22% | 14 | 400 |
|
||||
| **orig** | per **phase** | 13.04M | — | 14 | 449 |
|
||||
| **deferred** | once, after **whole build** | 13.37M | +3% | 10 | 425 |
|
||||
| **deferred** | once, after **whole build** | 12.89M | −1% | 12 | 425 |
|
||||
| **lean** | per **gate** | 13.41M | +3% | 28 | 390 |
|
||||
|
||||
## The two big findings
|
||||
@ -116,5 +116,5 @@ process intensity.
|
||||
_Artifacts in this repo: `FINDINGS.md` (this summary), `RESULTS-campaign.md` (per-variant stats +
|
||||
ratios + full raw table), `RESULTS-campaign.md.data` (raw rows), `analyze.py` (regenerates the
|
||||
analysis), `run-harness-bench.sh` / `run-solo-bench.sh` (the runners), `plans/calc/` (the task), and
|
||||
the six `engine/examples/builder-adversary*` variants. `deferred` is N=3 here and is being finalized
|
||||
to N=5; its median is stable (spread 1.19×)._
|
||||
the six `engine/examples/builder-adversary*` variants. All variants are N=5 (two `deferred` and the
|
||||
`min`/`lean` wedge/limit failures excluded; see RESULTS for the raw rows)._
|
||||
|
||||
@ -1,6 +1,6 @@
|
||||
# Full-harness benchmark — campaign analysis
|
||||
|
||||
Real `agents.py up` Builder/Adversary loop pair + watchdog through the 3-phase calculator to SEQUENCE-COMPLETE. Both loops on Sonnet. Tokens summed from each loop's session transcript; commits = work-repo commit count; LOC = non-blank `calc/*.py` lines (code + tests). 28 successful runs of 30 total.
|
||||
Real `agents.py up` Builder/Adversary loop pair + watchdog through the 3-phase calculator to SEQUENCE-COMPLETE. Both loops on Sonnet. Tokens summed from each loop's session transcript; commits = work-repo commit count; LOC = non-blank `calc/*.py` lines (code + tests). 30 successful runs of 33 total.
|
||||
|
||||
## Per-variant total tokens (successful runs)
|
||||
|
||||
@ -11,7 +11,7 @@ Real `agents.py up` Builder/Adversary loop pair + watchdog through the 3-phase c
|
||||
| builder-adversary-stateless | 5/5 | 10,122,375 | 10,735,401 | 9,992,834 | 13,009,792 | 1.30x |
|
||||
| builder-adversary-lean | 5/6 | 13,409,349 | 13,216,582 | 12,101,355 | 13,815,595 | 1.14x |
|
||||
| builder-solo | 5/5 | 2,773,634 | 2,744,840 | 2,417,528 | 2,948,467 | 1.22x |
|
||||
| builder-adversary-deferred | 3/3 | 13,366,800 | 13,863,041 | 12,888,082 | 15,334,242 | 1.19x |
|
||||
| builder-adversary-deferred | 5/6 | 12,888,082 | 12,410,637 | 9,610,923 | 15,334,242 | 1.60x |
|
||||
|
||||
## Efficiency ratios — min / median / max (successful runs)
|
||||
|
||||
@ -24,8 +24,8 @@ tokens/sec excludes runs flagged `LIMIT` (a usage-limit pause inflates duration
|
||||
| builder-adversary-stateless | 21,802 / 27,799 / 30,861 | 10,544 / 11,620 / 12,755 | 697,172 / 765,282 / 778,644 |
|
||||
| builder-adversary-lean | 28,077 / 33,238 / 38,966 | 12,416 / 13,523 / 14,403 | 432,191 / 478,905 / 575,650 |
|
||||
| builder-solo | 6,029 / 6,611 / 6,969 | 6,542 / 6,715 / 7,020 | 392,494 / 483,506 / 737,117 |
|
||||
| builder-adversary-deferred | 31,451 / 33,827 / 34,537 | 12,170 / 13,105 / 15,343 | 1,277,854 / 1,336,680 / 1,841,155 |
|
||||
| **all** | 6,029 / 29,024 / 38,966 | 6,542 / 12,170 / 15,814 | 392,494 / 705,228 / 1,841,155 |
|
||||
| builder-adversary-deferred | 20,107 / 31,451 / 34,537 | 12,170 / 13,349 / 15,343 | 739,302 / 1,277,854 / 1,841,155 |
|
||||
| **all** | 6,029 / 28,410 / 38,966 | 6,542 / 12,416 / 15,814 | 392,494 / 716,723 / 1,841,155 |
|
||||
|
||||
## Per-variant medians (commits / LOC / duration)
|
||||
|
||||
@ -36,15 +36,15 @@ tokens/sec excludes runs flagged `LIMIT` (a usage-limit pause inflates duration
|
||||
| builder-adversary-stateless | 14 | 400 | 900 |
|
||||
| builder-adversary-lean | 28 | 390 | 960 |
|
||||
| builder-solo | 5 | 426 | 420 |
|
||||
| builder-adversary-deferred | 10 | 425 | 1020 |
|
||||
| builder-adversary-deferred | 12 | 425 | 840 |
|
||||
|
||||
## Correlations with total tokens (pooled, n=28)
|
||||
## Correlations with total tokens (pooled, n=30)
|
||||
|
||||
| tokens vs | Pearson r |
|
||||
|---|--:|
|
||||
| duration | +0.83 |
|
||||
| commits | +0.65 |
|
||||
| LOC | +0.01 |
|
||||
| commits | +0.64 |
|
||||
| LOC | -0.00 |
|
||||
|
||||
## All runs (raw)
|
||||
|
||||
@ -80,5 +80,8 @@ tokens/sec excludes runs flagged `LIMIT` (a usage-limit pause inflates duration
|
||||
| builder-adversary-deferred | 1 | YES | | 13,366,800 | 1020 | 10 | 425 | 31,451 | 13,105 | 1,336,680 |
|
||||
| builder-adversary-deferred | 2 | YES | | 12,888,082 | 840 | 7 | 381 | 33,827 | 15,343 | 1,841,155 |
|
||||
| builder-adversary-deferred | 3 | YES | | 15,334,242 | 1260 | 12 | 444 | 34,537 | 12,170 | 1,277,854 |
|
||||
| builder-adversary-deferred | 4 | NO | | 8,536,729 | 2700 | 6 | 146 | 58,471 | 3,162 | 1,422,788 |
|
||||
| builder-adversary-deferred | 5 | YES | | 9,610,923 | 720 | 13 | 478 | 20,107 | 13,349 | 739,302 |
|
||||
| builder-adversary-deferred | 1 | YES | | 10,853,138 | 780 | 12 | 421 | 25,779 | 13,914 | 904,428 |
|
||||
|
||||
_Stats over successful runs. `LIMIT` = the run hit a usage-limit pause (duration/tok-sec distorted, token total fine). Repos kept under the run root for analysis._
|
||||
|
||||
@ -29,3 +29,5 @@ builder-adversary-deferred 1 YES 7375559 5991241 13366800 1020 10 425
|
||||
builder-adversary-deferred 2 YES 7803666 5084416 12888082 840 7 381
|
||||
builder-adversary-deferred 3 YES 8034336 7299906 15334242 1260 12 444
|
||||
builder-adversary-deferred 4 NO 4589433 3947296 8536729 2700 6 146
|
||||
builder-adversary-deferred 5 YES 5294341 4316582 9610923 720 13 478
|
||||
builder-adversary-deferred 1 YES 5968601 4884537 10853138 780 12 421
|
||||
|
||||
Reference in New Issue
Block a user