Ask HN: Why call it "inference" instead of just "model hosting"?

5 points | by bluebic 2 hours ago

5 comments

  • dlcarrier 11 minutes ago
    Inference is what you do with the model. It's not an executable, so you don't run a model directly, instead a separate program runs and that program reads from the model. Also, hosting can be used to mean running inference on a model, but it could also be used to mean just storing the files and possibly making them available for download, so it's a bit more vague.
  • dtagames 1 hour ago
    Like so many things in computing, we like to make up words and also reuse old ones for completely different things.

    I'd say "hosting" means making something available to you in the cloud. Model makers don't offer that.

    They sell "inference," which is a compute task with real hardware costs for them. The task runs against their model, which is not hosted for you.

  • mrhottakes 1 hour ago
    Inference sounds cooler and more mystical. Any old company can host something, "running inference" requires 10x rock star engineers and a CEO that acts like a badass who wears a leather jacket and has Thoughts about demographics.
    • rubylimetea 1 hour ago
      This literally has to be it. The people that say it tend to say it a lot.
  • bitpush 1 hour ago
    Same difference between S3 bucket and Google Photos (web). Both "host" images but one provides an experience on top of the underlying assets.
    • rubylimetea 1 hour ago
      That's interesting, the idea that hosting implies a front-end (whether UI or API).

      So it's similar to why we don't call Heroku or Vercel "hosting" or "compute" because it's more of a service (though "cloud" and "platform" are pretty vague too).

  • seydor 1 hour ago
    Are you really hosting the model? Are you making its bed, cooking its food and cleaning up for it?