跳到正文
Amp Chronicle·· 2026-06-18AI 評分49

A Faster Librarian

A Faster Librarian

AI 導讀

Librarian 改用不啟用 reasoning 的 GPT-5.5,搜尋速度提升約 3 倍、成本降低 43%,品質維持相同。內部評測中,平均延遲由 237s 降至 81s,F1 平均分數由 0.47 升至 0.48,平均成本由 $1.21 降至 $0.69。約四分之一的提速來自 OpenAI 的 websocket mode,其餘來自改用 GPT-5.5。

正文

The Librarian is now ~3x faster and 43% cheaper, with the same quality.

It now runs on GPT-5.5 (no reasoning) with websocket mode and an updated system prompt that encourages more parallel exploration. The Librarian fires ~8 tool calls in parallel per turn, up from ~3 with Sonnet, and wraps up a search in ~5 turns instead of ~15.

In our internal eval, about a quarter of that speedup comes from OpenAI's websocket mode and the rest from switching to GPT-5.5 with no reasoning:

Sonnet-4.6 (medium) GPT-5.5 (none)
Latency (mean) 237s 81s (2.9x faster)
↳ gain from websocket — ~1.3x
↳ gain from model — ~2.2x
Quality (F1, mean) 0.47 0.48
Average cost $1.21 $0.69

Here's a comparison:

How does Kubernetes' HorizontalPodAutoscaler handle missing pod metrics when scaling down — does it assume missing pods are at 100% of their resource requests, or 100% of the target utilization? Cite the function and logic in the source.

Sonnet 4.6 (left) took 2 minutes and cost $1.08, while GPT-5.5 (right) took 40 seconds and cost just $0.47.

來源:Amp Chronicle · ampcode.com