‹ BackHN Continuity

Thread

Gemini 4 Argon

1699 points · 1187 comments · bradleyg223

  1. taylorfinley · · focus · HN ↗
    Ten days ago I had an experience with Gemini 3.8 flash that made me wonder if I was being routed to a different model under test. I was trying to use rocm with llama.cpp on my 128gb Strix Halo but could only get it to run Vulkan. I pasted the error message into agy and it proceeded to attach GDB to my GPU driver, reverse-engineer the kernel queue ioctl interface, and author an LD_PRELOAD C shim to get ROCm llama.cpp working on my Strix Halo. My jaw was hanging open the whole time.

    Edit to add the fix: <a href="https:&#x2F;&#x2F;gist.github.com&#x2F;birep&#x2F;6f2c8d490c7a29820997d57bd654c351" rel="nofollow">https:&#x2F;&#x2F;gist.github.com&#x2F;birep&#x2F;6f2c8d490c7a29820997d57bd654c3...

    1. alightsoul · · focus · HN ↗
      Please tell me you published your findings even as an issue on the llama.cpp GitHub
      1. warkdarrior · · focus · HN ↗
        Why? Anyone can run that prompt.
        1. aspect0545 · · focus · HN ↗
          Not everybody has access to AI. More than that, every prompt uses insane amounts of natural resources. So why not share it.
          1. AuthAuth · · focus · HN ↗
            They dont understand the fix so sharing a vibe coded patch is upstream spam. They should submit a bug report and their findings. (Written by them not AI)
Open on Hacker News to reply ↗

Unofficial Hacker News client; not affiliated with Y Combinator.