logoalt Hacker News

rahimnathwani • today at 6:26 PM • 2 replies • view on HN

Can anyone explain how this is possible?

  Developers can update Claude’s instructions mid-task without breaking the prompt cache or routing the update through a user turn. This can be used in a given harness to update permissions, token budgets, or environment context as an agent runs.
Does this means the instructions are no longer just something in the early part of the conversation? (If they were, changing them would invalidate the KV cache. no?)

Replies

2001zhaozhao • today at 8:14 PM

Perhaps they trained it with a new special system instruction token that is specifically trained to produce the same result as changing the system prompt, but is inserted into the prompt mid-conversation?

pornel • today at 8:22 PM

The commands they list are app management, not part of LLM context. It's a bugfix for a needlessly delayed UI, not a model capability.