mfowler
3bf3316572
Capstone summary of the Builder/Adversary prompt + verification-cadence study: - adversary EXISTENCE costs ~4.7x (solo 2.8M vs ~13M); cadence is ~token-neutral - context hygiene is the one clean -22% win; minimal prompts -25% but test less - deferred review saves nothing (the one comprehensive pass is expensive) + late - cost is process not product (tokens~duration 0.83, ~commits 0.79, ~LOC -0.04) All results now in-repo: FINDINGS.md + RESULTS-campaign.md + raw .data + runners. (deferred N=3, finalizing to N=5.)
7 lines
69 B
Plaintext
7 lines
69 B
Plaintext
# runtime
|
|
.ao-state/
|
|
__pycache__/
|
|
*.pyc
|
|
*.tmp
|
|
RESULTS-harness.md.tmp
|