Deliverer of ideas for a living. Believer in internet autonomy, dignity. I upkeep instances of FOSS platforms like this for the masses. Previously on Twitter under the same handle. I do software things, but also I don’t.

  • 0 Posts
  • 137 Comments
Joined 2 年前
cake
Cake day: 2023年6月5日

help-circle



  • I would suggest that counselors / therpists, in fact, have backgrounds – educational and experiential – that support the ‘slick-talking BS’ you suggest, but that it is only slicktalking BS if you aren’t willing to consider the benefit you get from relating to them in the way they were trained to relate.

    This is important because the ‘relating’ is what has an impact more on you socially than the ‘slicktalk.’ It’s the ‘human-to-human’ part that sticks to us longer than self-help books, prompts us to be open and considerate for change, and even supports our eventual ability for understanding ourselves a little better.

    There is no ‘relating’ to an LLM. That LLM is weighted, in fact, to provide positive responses that meet the requesting of your text-based prompt.

    If, in an LLM therapy session, I suddenly flip the script and write, ‘Now pretend you are a far less confrontational therpaist who understands my feelings on X or Y that we’ve been talking about, and who doesn’t want to press me on it as much,’ then I am no longer even superficially attempting ‘relate.’ The cosplay of therapy is ripped away.

    The ‘relationship’ part of therapy cannot happen authentically with an LLM if I can still control the outcome.



  • chirospasm@lemmy.mltoLemmy Shitpost@lemmy.worldEvery time
    link
    fedilink
    arrow-up
    48
    ·
    edit-2
    1 个月前

    There’s a psychic in the movie that tells Peewee that the bicycle he lost is in the basement of the Alamo – the joke being that this is one of many instances where Peewee’s naivety gets the better of him, sending him off in another odd direction. The plot continually plays off his innocence.

    Nowadays, visitors to the Alamo reference the question on tours as a running joke.










  • GrapheneOS affords you the ability to have completely isolated and distinct phone profiles, where you can install all your required work apps. They are installed separate from your main profile, kind of like second or third phone. No need for a completely different device.

    GrapheneOS instantiates an improved version of this feature that Android already offers. It’s a great way to keep things separate. I do the same. Who wants to stuff their pockets or bags with more phones?

    You can read about that here.





  • Hello! I recently deployed GPUStack, a self-hosted GPU resource manager.

    It helps you deploy AI models across clusters of GPUs, regardless of network or device. Got a Mac? It can toss a model on there and route it into an interface. Got a VM on a sever somewhere? Same. How about your home PC, with that beefy gaming GPU? No prob. GPUStack is great at scaling what you have on hand, without having to deploy a bunch of independent instances of ollama, llama.ccp, etc.

    I use it to route pre-run LLMs into Open WebUI, another self-hosted interface for AI interactions, via the OpenAI API that both GPUStack and Open WebUI support!