• 0 Posts
  • 656 Comments
Joined 5 years ago
cake
Cake day: June 23rd, 2020

help-circle
  • verdigris@lemmy.mlto196@lemmy.world"AI" rule
    link
    fedilink
    arrow-up
    1
    ·
    edit-2
    22 hours ago

    Right, I mentioned that the more they’re used the more incentive there is to train new ones. But also it’s not like buying a product from the store which then creates a demand for a replacement, it’s much fuzzier and it’s difficult to point to any one user as increasing the demand for more models. Realistically I think we’ve gone well past the point where it makes sense to train general purpose LLMs any further, it’s drastically diminishing returns for marginally higher quality. The continued fervor is being driven by the same people that drove crypto and NFT prices way beyond reality: speculators and VC parasites trying to shove the new hype buzzword into anything they can get their hands on.


  • verdigris@lemmy.mlto196@lemmy.world"AI" rule
    link
    fedilink
    arrow-up
    45
    arrow-down
    7
    ·
    2 days ago

    This does misunderstand what actually costs the energy – it’s training the models that’s costly, not using the already trained ones. Although to be fair using them increases incentive for new ones to be trained… But yeah asking ChatGPT for a recipe idea isn’t burning an ounce of gasoline.