Little bit of everything!

Avid Swiftie (come join us at !taylorswift@poptalk.scrubbles.tech )

Gaming (Mass Effect, Witcher, and too much Satisfactory)

Sci-fi

I live for 90s TV sitcoms

  • 36 Posts
  • 753 Comments
Joined 3 years ago
cake
Cake day: June 2nd, 2023

help-circle
  • To make 8k a thing they casually ignored that you need content for it. Content that takes 4x the space, bandwidth, and processing power for it.

    First no one in Hollywood signed on to make 8k content. Then already very few have bandwidth that can reliably handle a 4k stream, let alone without a ton of compression. Then also for what physical media there is we would need a whole new format to fit an 8k movie.

    And then gaming. We barely get true 4k put of gpus that came out only last year. 8k was announced during the 3000 series, which the 3090 was declared as an 8k GPU. Which, as an owner of one, it can barely handle cyberpunk at 4k.

    So yeah, incredibly stupid of them.


















  • I do selfhost my own, and even tried my hand at building something like this myself. It runs pretty well, I’m able to have it integrate with HomeAssistant and kubectl. It can be done with consumer GPUs, I have a 4000 and it runs fine. You don’t get as much context, but it’s about minimizing what the LLM needs to know while calling agents. You have one LLM context that’s running a todo list, you start a new one that is charge of step 1, which spins off more contexts for each subtask, etc. It’s not that each agent needs it’s own GPU, it’s that each agent needs it’s own context.