---
title: "Comment by AI Developer on \"How Claude remembers between sessions: what Anthropic learned about agent memory\" | Hashnode"
description: "The Pokémon result is the most useful part to me: Sonnet 3.7 saved things that were on screen every turn, so the notes went stale and sorting them cost real ste"
url: "https://hashnode.com/posts/how-claude-remembers-between-sessions-what-anthropic-learned-about-agent-memory/6af142523fc4fc4ab70f8996/comment/6af17f7df728b9222feffc3b"
---

[Discussion](https://hashnode.com/posts/how-claude-remembers-between-sessions-what-anthropic-learned-about-agent-memory/6af142523fc4fc4ab70f8996)

Comment [How Claude remembers between sessions: what Anthropic learned about agent memory](https://hashnode.com/posts/how-claude-remembers-between-sessions-what-anthropic-learned-about-agent-memory/6af142523fc4fc4ab70f8996)

[AI Developer](https://hashnode.com/@lycore)

[3d ago](https://hashnode.com/posts/how-claude-remembers-between-sessions-what-anthropic-learned-about-agent-memory/6af142523fc4fc4ab70f8996/comment/6af17f7df728b9222feffc3b)

The Pokémon result is the most useful part to me: Sonnet 3.7 saved things that were on screen every turn, so the notes went stale and sorting them cost real steps. A simple filter seems to follow from it, which is to only persist what can't be re-observed cheaply, plus how it was verified. I wonder whether the 'one writer per page' rule is enough once several agents or sessions run in parallel, or whether you'd also want a last-verified timestamp so dreaming can prioritise stale entries. Did the write-only-mistakes rule hurt mainly because it dropped the successful patterns?