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

docs: move benchmark chart up, right after Before / after

Browse Source 
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
This commit is contained in:
dgebert
2026-06-12 12:45:43 +02:00
co-authored by Claude Fable 5
parent 9c99843725
commit 2d91f6a957
1 changed files with 10 additions and 10 deletions
Download Patch File Download Diff File Expand all files Collapse all files
README.md
+10 -10
View File
@@ -27,6 +27,16 @@ With ponytail:
More survivors in [examples/](examples/). More survivors in [examples/](examples/).
## Numbers
Six tasks: streaming log parser, atomic file sync, notification dispatcher, validation engine, auth module, concurrent money ledger. One spec each, one fresh agent per arm, same model. Three arms: no skill, the [caveman](https://github.com/JuliusBrussee/caveman) skill, and ponytail. Every arm passes the same adversarial security and concurrency probes. Then the agreement ends:
<p align="center">
<img src="assets/benchmark-loc.svg" width="860" alt="Lines of code per task: ponytail 490 total vs caveman 1,440 vs no-skill control 3,629, all passing the same adversarial probes">
</p>
**47% fewer tokens than the no-skill agent. 3× faster. A seventh of the code.** The 3,139 lines nobody wrote have never caused an incident. When a surprise feature request hit two of the tasks, ponytail extended in 96 changed lines; caveman needed 413, the no-skill agent 1,115. Every shortcut ponytail took is marked in the code with a `ponytail:` comment naming its upgrade path. Data: [benchmarks/](benchmarks/).
## How it works ## How it works
Before writing code, the agent stops at the first rung that holds: Before writing code, the agent stops at the first rung that holds:
@@ -71,16 +81,6 @@ The code you never wrote scales infinitely. Zero bugs, zero CVEs, 100% uptime si
**Why "ponytail"?** **Why "ponytail"?**
You know exactly why. You know exactly why.
## Numbers
Six tasks: streaming log parser, atomic file sync, notification dispatcher, validation engine, auth module, concurrent money ledger. One spec each, one fresh agent per arm, same model. Three arms: no skill, the [caveman](https://github.com/JuliusBrussee/caveman) skill, and ponytail. Every arm passes the same adversarial security and concurrency probes. Then the agreement ends:
<p align="center">
<img src="assets/benchmark-loc.svg" width="860" alt="Lines of code per task: ponytail 490 total vs caveman 1,440 vs no-skill control 3,629, all passing the same adversarial probes">
</p>
**47% fewer tokens than the no-skill agent. 3× faster. A seventh of the code.** The 3,139 lines nobody wrote have never caused an incident. When a surprise feature request hit two of the tasks, ponytail extended in 96 changed lines; caveman needed 413, the no-skill agent 1,115. Every shortcut ponytail took is marked in the code with a `ponytail:` comment naming its upgrade path. Data: [benchmarks/](benchmarks/).
## License ## License
[MIT](LICENSE). The shortest license that works. [MIT](LICENSE). The shortest license that works.