Multi-user collaboration via agents is based, fundamentally, on the ability of collaborators to prompt inject your agent.

· Bits and Bobs 9/21/26
  • Multi-user collaboration via agents is based, fundamentally, on the ability of collaborators to prompt inject your agent.
    • That's a dangerous ability, so you should only collaborate with people you trust deeply.
    • Would you trust them alone in your house for an afternoon?
    • If not, then you shouldn't allow them to inject your agent.