自我學習代理
自我學習代理會根據工作過程中發生的事情來改進:你做出的修正、任務的結果、你接受或拒絕的編輯。它改變的是自己的行為,而不只是當下的上下文。
自我學習代理會根據工作過程中發生的事情來改變自己的運作方式,而不只是依賴你當下告訴它的內容。
這種學習是狹窄且具體的,這正是它有用的原因。它不會重新訓練模型,而是將學到的內容記錄為記憶,並在下次套用:
- 一個修正。 你說「不,這裡用箭頭函式」。這就成為一條規則,並從此生效。請參閱規則與事實。
- 一個任務結果。 在任務中實際有效的方法,以及它必須重做的地方,會影響它處理下一個任務的方式。請參閱代理如何在工作時學習。
- 你保留的內容。 你接受和拒絕的編輯是關於你偏好的訊號,這就是為什麼結果會改善,而你不需要撰寫規格。
有兩個界線值得了解。它只在記憶開啟的表面上學習,而不會在無痕聊天中學習,後者設計上就是唯讀的。而且它所學到的內容屬於你,你可以檢查和移除:請參閱變更或忘記記憶。
Related articles
- Agent memoryAgent memory is what an agent stores between sessions and brings back when it is relevant: standing rules, facts, studied material, and short summaries of past conversations.
- AI agent with a memoryAn AI agent with a memory is one that keeps what it learns about you and your work, attaches it to your account rather than to one app, and applies it wherever you use the agent next.
- How an agent learns as it worksDropstone is a self-learning agent. It records what it learns from corrections, from finished work, and from sources you ask it to study, and it uses that the next time without being told. Here is the loop.
- Rules and factsDropstone keeps two kinds of memory. Standing rules apply to every task without being searched for. Facts are recalled only when they are relevant. Here is why the difference matters and how it decides.
Ctrl+I