Anthropic测试Claude选择性记忆方法
AI 总结
Anthropic的测试显示,Claude采用仅记录策略和已验证规则的精简笔记,效果优于保存全部交互步骤的详尽归档。其Dreaming流程会在空闲时检查早期会话记录、纠正错误笔记并整理结构化知识,包括用约35万份Stainless文档构建的维基。Anthropic也承认,记笔记会分散智能体注意力,Dreaming会增加算力和延迟,记忆库仍需维护,且相关评测均来自公司内部。
深度见解
这项研究提供了改进持久化AI智能体记忆的具体方法:通过筛选记录并事后纠正错误,避免把每次交互都塞入后续会话。
Anthropic says the key to agent memory is knowing what to forget, not how much to store
Jonathan Kemper View the LinkedIn Profile of Jonathan Kemper
Nov 16, 2026

Anthropic
Key Points
- Anthropic tested how Claude can store information in note files across sessions and retrieve it for later tasks.
- The tests showed that selectively recording strategies and rules works better than logging every step, which overwhelms models with outdated data.
- Through a post-session process called "Dreaming," the system analyzes earlier session transcripts during idle periods to independently correct faulty notes and build structured knowledge collections.
#Anthropic#Claude#Dreaming#Claude Managed Agents#Stainless#Claude Sonnet 3.7#Claude Fable 5#Claude Opus 4.7#Claude Sonnet 4.6#Letta#UC Berkeley