The Inference Hardware Revolution of 2026

 (spectrum.ieee.org)

41 points | by vinhnx 4 hours ago

2 comments

  • geoffbp 38 minutes ago
    > And Anthropic is paying LLM competitor SpaceXAI over a billion dollars per month to lease spare compute

    I knew of this but not the $ amount. Wow

    [-]
    • cma 25 minutes ago
      Big money from taking Tesla's place in line for an Nvidia shipment during a huge shortage without compensation.
  • _superposition_ 51 minutes ago
    Excellent article. I believe the majority of benchmark performance gains moving forward will come from this side of the stack enabling faster iteration/recursion.