← Back to context

Comment by esafak

9 hours ago

Hear, hear. Even if the model fits, a few tokens per second make no sense. Time is money too.

If I can start an agent and be able to walk away for 8 hours, and be confident it's 'smart' enough to complete a task unattended, that's still useful.

At 3 tk/s, that's still 100-150 pages of a book, give or take.

Maybe for a coding agent, but a daily/weekly report on sensitive info?

If it were 2016 and this technology existed but only in 1 t/s, every company would find a way to extract the most leverage out of it.

  • If they figured out it can be this useful in 2016 running 1 t/s, they would make it run at least 20 t/s by 2019

  • But it's 2026 and 'secure' (by executive standards) hosted options exist.

    • > 'secure' (by executive standards)

      "Secure" in the sense that they can sue someone after the fact, instead of preventing data from leaking in the first place.