News for hackers. Stuff that matters.
Re:Ask HN: Examples of Agentic LLM Systems in Production? by wpietri on Monday December 16, 2024 @11:02AM (#42432263)
My take is that if the LLM outputs text for humans to read, that's not an agent. If it's making API calls and doing things with the results, that's an agent. But given the way "AI" has stretched to become the new "radium" [1], I'm sure "agent" will shortly become almost meaningless.

[1] https://en.wikipedia.org/wiki/Radium_fad

Re:Ask HN: Examples of Agentic LLM Systems in Production? by zdifferentiator on Monday December 16, 2024 @05:00PM (#42435932)
^^ best definition.

Right now they are "read-only" which I would call a persona