wangjunxiao/ponytail
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

docs: state the single-shot limitation honestly

Browse Source 
The benchmark is single-shot (one prompt, one completion); it does not measure
a real multi-turn agent session, where the ruleset re-injects and the ladder
deliberates every turn. Adds that caveat to the README, and corrects the
benchmarks/README note that claimed caching widens the gap "in ponytail's
favor" (unverified, and a measured agentic A/B in #121 found the opposite can
happen). Per-session cost can land either way.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
This commit is contained in:
Emeriko
2026-06-17 04:20:19 +02:00
co-authored by Claude Opus 4.8
parent b4c3659f69
commit 399b1dedd5
2 changed files with 2 additions and 2 deletions
Download Patch File Download Diff File Expand all files Collapse all files
README.md
+1 -1
View File
@@ -52,7 +52,7 @@ Five everyday tasks (email validator, debounce, CSV sum, countdown timer, rate l
**80-94% less code, 42-75% less cost, and 3-6× faster than a no-skill agent, on every Claude model.** Every shortcut ponytail takes is marked in the code with a `ponytail:` comment naming its upgrade path. Reproduce it yourself: `npx promptfoo eval -c benchmarks/promptfooconfig.yaml`. Method and raw numbers: [benchmarks/](benchmarks/). Production-grade tasks, where an unconstrained agent bloats far more, are written up in [benchmarks/results/](benchmarks/results/).
**That is the byproduct, not the pitch.** These are Claude numbers, and they vary by model. Capable instruction-following models follow the ladder and write far less, cheaper and faster. Terse reasoning models can go the other way: the ladder is a deliberation step, so the model spends thinking tokens working through the rungs before it saves any output, and together with the always-on ruleset that can cost more than the shorter code saves. On GPT-5.5 it does. The rule was never "fewest tokens." It is: write only what the task needs, and never cut validation, error handling, security, or accessibility. The code ends up small because it is necessary, not golfed, and that is the part that stays maintainable. Lower cost and latency are a side effect on the models that follow it.
**That is the byproduct, not the pitch.** These are Claude numbers, and they vary by model. Capable instruction-following models follow the ladder and write far less, cheaper and faster. Terse reasoning models can go the other way: the ladder is a deliberation step, so the model spends thinking tokens working through the rungs before it saves any output, and together with the always-on ruleset that can cost more than the shorter code saves. On GPT-5.5 it does. And all of this is single-shot, one prompt in and one answer out: a real agent session re-injects the ruleset and runs the ladder every turn, which this benchmark does not measure, so per-session cost can land either way. The rule was never "fewest tokens." It is: write only what the task needs, and never cut validation, error handling, security, or accessibility. The code ends up small because it is necessary, not golfed, and that is the part that stays maintainable. Lower cost and latency are a side effect on the models that follow it.
## How it works