TGViewer
HN Best Comments HN Best Comments @hn_best_comments · 4.16K subscribers
Post #33802 340
Re: Gemini 4 Argon

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.

taylorfinley, 1 hour ago
Open in Telegram All posts from @hn_best_comments
More from @hn_best_comments
  1. Oct 1, 2026Re: Gemini 4 Argon Google has TPUs, a frontier model, a completely separate and lucrative…
  2. Sep 30, 2026Re: Gemini 4 Argon > We’ll continue to gather feedback from early testers as we iterate on…
  3. Sep 30, 2026Re: Gemini 4 Argon The important take away here: the leapfrogging we’ve seen this year doe…
  4. Sep 30, 2026Re: Gemini 4 Argon My girlfriend, you wouldn't have met her, she lives in Canada, has seen…
  5. Sep 30, 2026Re: Burning Man death rates – A short lesson in statistics Some of this is selection bias,…
  6. Sep 30, 2026Re: Backblaze drive stats for Q2 2026 In 2013 Backblaze saw ~14% avg failure rate at 3 yea…
Threads Profile ViewerView any public Threads profile without an account.Open ThreadLook →Writing with AI? Make it sound human.Metric37 rewrites AI drafts so they read naturally. Free AI detector, 1,500 words free.Try Metric37 →