跳到正文
𝕏 Aravind Srinivas(x.com)·· 3 天前精選品質評分70
重點導讀

AI 助理常要重複處理類似工作,使用者也得自己新增技能。

  • Perplexity Computer 現在會讀取過去的工作紀錄,找出一再出現的做法。
  • 證據夠多時,就提議新增或更新技能。每位使用者都能取得的內建技能,還會先用失敗情境測試並經工程師檢查,才會正式推出。在一項為期 8 週的隨機測試中,72.9% 的使用者至少得到一項個人技能,手動新增技能的使用者則有 6.5%。
  • 工具呼叫失敗減少 11%,使用者不滿意的對話減少 7.6%,成本和速度沒有可測量的變化。

AI 伴隨問答

自備 Key 深度分析

針對這篇報導有疑問?可直接點選快捷問題或向 AI 追問背景脈絡與技術細節:

推薦理由

八週隨機測試比較自動整理技能與使用者手動新增的情況,並呈現工具呼叫失敗和使用者不滿意對話的變化。

Aravind Srinivas
Aravind Srinivas@AravSrinivas
·3 天前
𝕏

Sharing new research on self-improving skills in Perplexity Computer. Brain, which already maintains a knowledge wiki about your work, now also writes and updates agent skills for you based on your past sessions. An improvement agent reads the full session trajectories (tool calls, reasoning, results), finds recurring patterns, and only proposes a new skill or an update when there’s enough evidence. Built-in skills that every user gets go through paired replay on failure scenarios and engineer review before any change goes live. In an 8-week randomized test on production traffic, 72.9% of users got at least one new personal skill vs 6.5% who added one manually. Tool call failures dropped 11% and dissatisfied threads dropped 7.6%, with no measurable change in cost or latency.

推文來源 · X (Twitter)在 X 參與討論

讀者討論

理性交流 · 即時討論