• dorin_vlas 2 days ago |
    Interesting...
  • simonw 2 days ago |
    I'm always interested in seeing which definition of "AI agents" a group is using (which they inevitably seem to assume is obvious and shared by everyone else.)

    In this case it looks like it's "AI decision-making system that learns through reinforcement learning to handle complex tasks" - with training an algorithm to control traffic lights at many intersections in a city as their illustrative example.

    • falseprofit 4 hours ago |
      What alternative definitions(s) have you found to be most common?
      • simonw 2 hours ago |
        Among software engineers "LLM with access to tools" shows up a lot. Or sometimes "LLM in a loop" or "LLM on a schedule / that can respond to triggers". Or even just an LLM with a custom system prompt.

        Thermostat is common: an AI system that can react to its environment and continually make changes based on that ongoing feedback.

        The ability to act on a loop in order to reach a predefined goal. I think of ChatGPT Code Interpreter as a good example of that one.

        There's a more complex definition that requires the "agent" to have a memory and access to tools and the ability to run in a loop towards a goal and continually learn from what it's doing.

        A common one among less-technical groups is an assumption that an AI agent is anything that's similar to a human travel agent - something that goes away and arranges something on your behalf.

        LangChain have a "what is an AI agent?" piece - https://blog.langchain.dev/what-is-an-agent/ - that punts on the whole idea of providing a binary definition and instead talks about "agentic" as more of a spectrum. They also define an agent as something that "uses an LLM to decide the control flow of an application" - I don't fully understand what that means though.

        I collected several hundred more in a bunch of Twitter replies a while back, which I've been meaning to attempt to group into categories: https://twitter.com/simonw/status/1843290729260703801 - partially scraped collection of replies here: https://gist.github.com/simonw/bdc7b894eedcfd54f0a2422ea8fea...

        There's a cynical definition that I quite enjoy: LLMs that do something useful.

  • j45 2 days ago |
    In case anyone may be researching lately, I'd appreciate learning about potentially any useful content, tools, or suggestions to build or train more AI agents.

    CrewAI is already on the radar :)

    • d4rkp4ttern a day ago |
      Have a look at Langroid [1], a multi-agent LLM framework from CMU/UW-Madison researchers (I am lead dev). It does not use any other LLM library (CrewAI uses LangChain). We started building Langroid in Apr 2023 as an agent framework from the ground up, with a particular focus on an agent orchestration mechanism that seamlessly handles inter-agent hand-off as well as Tool/Function-handling.

      [1] https://github.com/langroid/langroid

  • pama 2 days ago |