LM Studio Bionic: the AI agent for open models

(lmstudio.ai)

68 points | by minimaxir 2 hours ago ago

23 comments

  • gehsty 31 minutes ago

    This kind of thing just makes me think Apple will get to a point where they have good enough local models and good enough harnesses for doing things, and most normal people will just use them… Does the LLM become another interface to computing?

    • ibero 26 minutes ago

      i agree.

      i believe that for most people on the street, for most tasks, a Chat GPT 3.5 era LLM is sufficient enough. sprinkle in tool calling and other things, and that becomes enough. if you can prioritize that level of a model on-device (baking it in etc), then you can bifurcate AI users between those unwilling to pay and those who are willing to pay A LOT for frontier model performance.

    • dominotw 10 minutes ago

      or the other way where primary interfaces ppl use computing arent apple devices like laptops and phones.

  • thehamkercat an hour ago

    A friendly reminder that both LM Studio app and now this new LM Studio Bionic app are closed source.

    Since most people are unaware of this fact.

    • nodja 7 minutes ago

      Yup, it's the main reason I don't use LM studio more. I only use it to try out new models/quants, then use llama.cpp directly to host them. LM Studio also doesn't do stuff like audio input and often has bugs that pure llama.cpp doesn't so it can be a net negative for certain use cases.

    • cpursley 8 minutes ago

      Does anyone know about their stack - is it a native app? It's fairly well designed for what it is in terms of desktop apps.

    • minimaxir an hour ago

      And? Is that a scandal?

      • thehamkercat 38 minutes ago

        Not a scandal ofc, but people use local models mostly for privacy

        and using a closed-source, VC-backed app that might change anything in the next update might not be best for privacy

      • speedgoose 41 minutes ago

        No, but you are a lot more vulnerable to enshittification and you don’t have the advantages of open source applications.

        It’s an important criteria to have in mind when you select an application.

      • felooboolooomba 30 minutes ago

        I'm interested in your thought process. How did you get from his initial statement opening of "A friendly reminder ..." to thinking that this was a scandal?

        • minimaxir 14 minutes ago

          It's a common discussion trope to imply malfeasance in response to good news, which is a way to non-constructively shut down a conversation particularly without elaboration. In this particular case I legit didn't understand what the OP was actually implying because they did not elaborate.

      • cyanydeez an hour ago

        some people want to make money, others want to improve social progress.

        Happy to clarify which is who and who is which.

        • radial_symmetry 42 minutes ago

          You can do both

          • folkrav 5 minutes ago

            Sure. I still don't think it's particularly controversial to acknowledge that the two don't necessarily align either, and that neither really incentivizes the other.

            Less unanimous and debatable, but many would say they more often do not align than the opposite.

        • watwut 40 minutes ago

          No one involved in LLMs want to improve social progress. That is simply not part of the equasion.

      • NamlchakKhandro 36 minutes ago

        Yes.

        Is that a problem for you comrad?

        • cicko 30 minutes ago

          It is, cowboy

  • blitzar an hour ago

    I am not sure I get this. It seems on first glance like just another harness ...

    • Normal_gaussian an hour ago

      Built to work with lmstudio, one of the leading easy to use local model servers. LMStudio is the closest to plug-and-play without sacrificing play that I've seen; a harness that works well with it is nothing to sniff at. Its not earth shattering either.

      • blitzar 26 minutes ago

        I guess it lives or dies by the harness quality then - on open models run locally by plug and players and models that fit onto peoples laptops that is going to be quite the handicap to overcome.

        I run lmstudio personally with a range of harnesses (open and closed) and can't say there is that much of a leap to getting everything talking https://lmstudio.ai/docs/integrations

      • cjonas 22 minutes ago

        Wouldn't most opensource harnesses work with lmstudio? I assume it has an "openai" style chat API like every other model provider? What's special about it vs langchain deep agents or pi or pydantic-ai?

      • tokai 9 minutes ago

        How does it work with lmstudio? Its a separate standalone application.

    • minimaxir an hour ago

      If you want to use local models, it's more ergonomic than fussing with GGUFs or using LM Studio as a server host and setting up the link to an agent yourself. Although, the model selector is the same as with LM Studio itself which can be overwhelming if you don't know what to look for.