Akhetonics Photonic Computing: 1,000x Faster CPUs

 (medium.com)

28 points | by peter_d_sherman 3 days ago

9 comments

  • akifbayram 3 minutes ago
    The channel's other uploads may be giving us a glimpse into this project's future.
  • himata4113 7 minutes ago
    This comes up every couple of years, but it hasn't seem to have made any advances since the first time I've seen this.
  • amelius 23 minutes ago
    So they have some kind of nonlinear material that can make light modulate other light, that they managed to get working at teraherz frequencies?

    Sounds incredible, as in: can't believe it.

    By the way, isn't Nvidia researching this?

    [-]
    • octoberfranklin 20 minutes ago
      Yes; this material is called "snake oil".
      [-]
      • amelius 16 minutes ago
        Let's see if the investors bite.
  • 12ah5kl 1 hour ago
    Interesting topic, unreadable due to sloppification.
    [-]
    • yuhmahp 17 minutes ago
      Now it's a good case to use your own ai to un-sloppify
  • dvh 1 hour ago
    > Photonics

    So also 1000x smaller integration

    [-]
  • mbfg 1 hour ago
    interesting that it is still 2 bit
  • natas 1 hour ago
    This has been tried by Cray like 15 years ago and the university of Colorado 11 years ago; there were also other initiatives, all failed.

    I'm not excluding that now we have more budget/time/AI to make it work (if it can), I'd just say exercise caution reading this (very AI slop) article (and anything that looks too good to be true)

  • peter_d_sherman 3 days ago
    [dead]
  • Lucasoato 54 minutes ago
    [flagged]