Loading page...Загружаем страницу...正在加载页面...
AtlasRepo

I Gave an LLM the Keys to Rewrite Its Own Prompt — Then Built a Gate That Said No 4,150 Times

说明与用途

使用本地 Qwen 4B 模型和六项确定性检查的门,构建了安全的提示自我改进管道,实现零误报并捕获所有对抗性编辑。

问题

Building a self‑improving prompt optimizer risks unsafe edits; the gate must be deterministic and conservative to prevent drift and false promotions.

结果

Zero false positives, 5/5 adversarial edits caught, 12/12 Docker tests passed, 489/489 unit tests passed, 4,150 LLM calls at $0.00 cost.

工作流

  • 1. Agent executes task and stores trace in SQLite
  • 2. Feedback Analyzer (LLM) reviews trace and proposes prompt edits
  • 3. A/B Test Engine runs candidate vs current prompt on a 40‑task set
  • 4. Promotion Gate applies six deterministic checks in order
  • 5. If all pass, promote; if near‑miss, log for human review; if reject, archive reasoning

证据

Gate false positive rate 0% (all runs, all domains)

来源

Sample floor — Minimum A/B trials completed. Default 5.

来源

4,150 LLM calls in the full field test: $0.00.

来源

  • 记录日期: 2026-09-07T04:07:34.035Z