home.social

#llmlimits — Public Fediverse posts

Live and recent posts from across the Fediverse tagged #llmlimits, aggregated by home.social.

fetched live
  1. @ariadne @shituationist

    Whenever someone declares #LLMs ded, check which wall they're pointing at, there are three and they keep getting smashed together.

    Attached plot: the one people wave around as a ceiling. Log-log axes though, that dashed diagonal is a power law holding over ten orders of magnitude. Chinchilla et.all.
    All it prices is compute against loss.

    The micro-outage forensics; failed requests, ergo no headroom, ergo scaling is dead, are fun but underdetermined.

    Deploys, autoscaler lag and load-shedding all look identical to 'ran out of GPUs' from userland.
    Frozen weights don't get tired: capacity pressure fails loudly, not stupid. The honest symptom is the 502. The dishonest one is quiet , quantize harder, trim context, route to the smaller model, same name on the box. Providers do that.sometime

    The money, though, sure fair cop. A quarter-trillion vendor backstop should make everyone's eye twitch. HOOOWEVER... (And its not something I wanna argue, still developing this argument)...
    A quarterly return is a shit metric for a magic genie that will put all the professionals out of work, forever.
    We all know capitalism sucks, and its funny that brologarchs are discovering it too.

    Just don't let a shaky business model stand in for a broken scaling law. Power laws have outlived plenty of companies.

    TLDR; Yes but no.

    #aiscaling #llmlimits

  2. @ariadne @shituationist

    Whenever someone declares #LLMs ded, check which wall they're pointing at, there are three and they keep getting smashed together.

    Attached plot: the one people wave around as a ceiling. Log-log axes though, that dashed diagonal is a power law holding over ten orders of magnitude. Chinchilla et.all.
    All it prices is compute against loss.

    The micro-outage forensics; failed requests, ergo no headroom, ergo scaling is dead, are fun but underdetermined.

    Deploys, autoscaler lag and load-shedding all look identical to 'ran out of GPUs' from userland.
    Frozen weights don't get tired: capacity pressure fails loudly, not stupid. The honest symptom is the 502. The dishonest one is quiet , quantize harder, trim context, route to the smaller model, same name on the box. Providers do that.sometime

    The money, though, sure fair cop. A quarter-trillion vendor backstop should make everyone's eye twitch. HOOOWEVER... (And its not something I wanna argue, still developing this argument)...
    A quarterly return is a shit metric for a magic genie that will put all the professionals out of work, forever.
    We all know capitalism sucks, and its funny that brologarchs are discovering it too.

    Just don't let a shaky business model stand in for a broken scaling law. Power laws have outlived plenty of companies.

    TLDR; Yes but no.

    #aiscaling #llmlimits

  3. @ariadne @shituationist

    Whenever someone declares #LLMs ded, check which wall they're pointing at, there are three and they keep getting smashed together.

    Attached plot: the one people wave around as a ceiling. Log-log axes though, that dashed diagonal is a power law holding over ten orders of magnitude. Chinchilla et.all.
    All it prices is compute against loss.

    The micro-outage forensics; failed requests, ergo no headroom, ergo scaling is dead, are fun but underdetermined.

    Deploys, autoscaler lag and load-shedding all look identical to 'ran out of GPUs' from userland.
    Frozen weights don't get tired: capacity pressure fails loudly, not stupid. The honest symptom is the 502. The dishonest one is quiet , quantize harder, trim context, route to the smaller model, same name on the box. Providers do that.sometime

    The money, though, sure fair cop. A quarter-trillion vendor backstop should make everyone's eye twitch. HOOOWEVER... (And its not something I wanna argue, still developing this argument)...
    A quarterly return is a shit metric for a magic genie that will put all the professionals out of work, forever.
    We all know capitalism sucks, and its funny that brologarchs are discovering it too.

    Just don't let a shaky business model stand in for a broken scaling law. Power laws have outlived plenty of companies.

    TLDR; Yes but no.

    #aiscaling #llmlimits

  4. A Bit of Security for Feb 22, 2024
    How we wrote the Client Server and Cooperative Processing research report – and why an LLM could never do it. Listen to this -
    youtu.be/aVx1HW2jDKc
    Let me know what you think in the comments below or at [email protected]
    #cybersecuritytips #LLMlimits #Clientserver #ntierapplications #BitofSec

  5. A Bit of Security for Feb 22, 2024
    How we wrote the Client Server and Cooperative Processing research report – and why an LLM could never do it. Listen to this -
    youtu.be/aVx1HW2jDKc
    Let me know what you think in the comments below or at [email protected]
    #cybersecuritytips #LLMlimits #Clientserver #ntierapplications #BitofSec

  6. A Bit of Security for Feb 22, 2024
    How we wrote the Client Server and Cooperative Processing research report – and why an LLM could never do it. Listen to this -
    youtu.be/aVx1HW2jDKc
    Let me know what you think in the comments below or at [email protected]
    #cybersecuritytips #LLMlimits #Clientserver #ntierapplications #BitofSec

  7. A Bit of Security for Feb 22, 2024
    How we wrote the Client Server and Cooperative Processing research report – and why an LLM could never do it. Listen to this -
    youtu.be/aVx1HW2jDKc
    Let me know what you think in the comments below or at [email protected]
    #cybersecuritytips #LLMlimits #Clientserver #ntierapplications #BitofSec