@Fingerthief - eviltoast

Web Dev Person / Ex Performance ECU Calibrations Person

  • 4 Posts
  • 39 Comments
Joined 1 year ago
cake
Cake day: July 3rd, 2023

help-circle

  • This project is entirely web based using Vue 3, it doesn’t use langchain and I haven’t looked into it before honestly but I do see they offer a JS library I could utilize. I’ll definitely be looking into that!

    As a result there is no LLM function calling currently and apps like LM Studio don’t support function calling when hosting models locally from what I remember. It’s definitely on my list to add the ability to retrieve outside data like searching the web and generating a response with the results etc…


  • Yep that’s a pretty good comparison!

    I’m curious on what you mean by sourcing training data in an ethical way? I know OpenAI has come under well deserved scrutiny for apparently using content that is hidden behind paywalls without purchasing it themselves in their training data. Which is quite unethical, but aside from that instance I’m interested in hearing some other concerns for my own education.

    In general there are definitely loads of models on places like Hugging Face that are fully open source and provide training data sources for many.

    I believe for Microsoft’s new Phi 3 models they actually generated synthetic data themselves for training as well which is an interesting approach that seems to yield good results.

    In the open source LLM world the new Meta Llama 3 models are the latest and greatest, I haven’t seen any cause for concerns with it yet. Might be worth looking into those!



  • Local models are indeed already supported! In fact any API (local or otherwise) that uses the OpenAI response format (which is the standard) will work.

    So you can use something like LM Studio to host a model locally and connect to it via the local API it spins up.

    If you want to get crazy…fully local browser models are also supported in Chrome and Edge currently. It will download the selected model fully and load it into the WebGPU of your browser and let you chat. It’s more experimental and takes actual hardware power since you’re fully hosting a model in your browser itself. As seen below.









  • Well you’ll probably really enjoy This Video haha!

    The MGU-H mode was on the “motor” so it doesn’t count for this challenge but still that’s the absolute most I can get out of the car!

    I’m right on the edge of my ability through a lot of this lap, proper sweaty attempt.

    I’ll run in the correct mode for an official lap if I end up needing to, no worries there. At most the advantage was a few tenths as ERS deployment per lap is limited.

    Moar people need to join up and give it a go!



  • Hah, funnily enough Alonso is my all time favorite driver and I have admired his driving style for many years.

    • Yeah Degna 1 is flat if you just close your eyes and huck it in!

    • I don’t think I’ve ever taken Spoon curve in any game or car and thought I did it right, it always feels so wrong to me. I think that attempt was the closest I’ve been to feeling I got it right.

    The 1:29’s are clearly within grasp for both of us, I feel I left a few tenths on the table at the hairpin alone with the lockup and horrible line.


  • Very nice lap! It definitely looks like you tend to be a driver with really smooth and clean inputs, I tend to wrestle things a bit as least in qualifying I’ve noticed in comparison. I’m always fascinated by driving style differences between drivers while also being relatively equal in speed.

    I just happened to have a set a new lap myself, just to give you a bit of a headache 😆



  • You know…I may have ran in hotlap mode as well just out of quali habit.

    I’ll have to run again in the default mode this weekend and post that time just to be sure. I don’t want any advantage haha

    Good thing you pointed that out lol

    Edit - Though I would argue for hotlaps it would make sense to be able to use whatever default onboard controls the vehicle has imo.


  • Thanks! I honestly had no idea what a decent lap was with this car/track hah.

    It’s definitely a track you have to be really precise at (in this car especially) otherwise you go slightly off line and run just wide enough in places to dip a wheel in the grass and around you go.

    Really really fun though, especially when you get it just right!

    Looking forward to seeing if I can improve a bit more this coming weekend. I’m sure you’ll catch up to me soon enough lmao.




  • SimpleDev@infosec.pubtoTechnology@lemmy.world*Permanently Deleted*
    link
    fedilink
    English
    arrow-up
    2
    ·
    edit-2
    1 year ago

    I disliked signal app wise, and Matrix app was a buggy mess for me and the 4 other people who tried to use it as well

    SimpleX was easy to setup and has been for the most part stable for all of us.

    Basically to answer your question, people like different things.

    SimpleX isn’t perfect by any means but it seems to be developed at a somewhat decent pace with noticeable improvements being made.