Live data from Hacker News

Viewing profile — steren

steren

HN member
Joined
Wed, Apr 20, 2011, 2:38 PM UTC
HN karma
2,428
Public activity
293 items

About steren

No profile information was provided.

Recent public activity

  1. comment
    Comment #49130174

    I don't understand your proposal Customer elements MUST have an hyphen. is the same as in HTML

  2. comment
    Comment #48512698

    Wasn't it the point of ... OpenAI?

  3. comment
    Comment #48417274

    The moment when I ran llama on my old gaming PC (using something called ChatGPT4All) was my "oh shit" moment: I was now talking... to my PC.

  4. story
  5. comment
    Comment #47007233

    Same in the US you know. Uncle Sam is very happy to take my tax money, but doesn't take my vote.

  6. comment
    Comment #46921285

    At Google we call it KTLO ("Keep The Lights On")

  7. story
  8. comment
    Comment #46381208

    Check out this sample of using gVisor to spin up code sandboxes (potentially running on Cloud Run): https://github.com/GoogleCloudPlatform/cloud-run-sandbox

  9. comment
    Comment #46258148

    I've also been creating HTML tools over the years when I couldn't find client-side only websites for PDF to SVG, CSV to Sheet, Audio to Video, Video to MP4. I list them at https://…

  10. comment
    Comment #45562735

    Same thing I was working on in 2018 already: Google Cloud Run ( https://cloud.run/ ) We just kept shipping, and shipping, and shipping...

  11. story
  12. story
  13. comment
    Comment #44909022

    I myself have wondered why VisionOS Safari wasn't more leaning into the idea that the DOM has semantics (e.g. ) and CSS is already able to convey depth information. I love the idea…

  14. comment
    Comment #44804225

    > I would never want to use something like ollama in a production setting. We benchmarked vLLM and Ollama on both startup time and tokens per seconds. Ollama comes at the top. We h…

  15. comment
    Comment #44381097

    Because Gemini CLI is OSS, you can also find the system prompt at: https://github.com/google-gemini/gemini-cli/blob/4b5ca6bc777...

  16. comment
    Comment #44197405

    > Because the pricing when creating an instance shows me the cost for the entire month Are you referring to the GCP pricing calculator? > This is just creating a GPU VM instance Ma…

  17. comment
  18. comment
    Comment #44185058

    Also, a GPU instance needs 5s to start. The test depends on how large the model is. So a "very small weak model" can lead much faster than 20s

  19. comment
    Comment #44183480

    > Google's pricing also assumes you're running it 24/7 for an entire month What makes you think that? Cloud Run [pricing page]( https://cloud.google.com/run/pricing ) explicitly sa…

  20. comment
    Comment #44182505

    Cloud Run PM lead here. Sign up for new GPU types at https://docs.google.com/forms/d/e/1FAIpQLSdZk5sCsDUjAoYQX-sq...

  21. comment
    Comment #44056885

    Curious: why not set up a custom domain?

  22. comment
    Comment #43927523

    GW is power. Gwh is energy. Energy is what matters when training a model. Please get your units right. In the meantime, down voted.

  23. comment
    Comment #43881624

    in the meantime, you can use https://www.npmjs.com/package/html-include-element

  24. comment
    Comment #43813932

    Icônes is just how to write icones in French.

  25. comment
    Comment #43009162

    No, we should teach React to beginners! ;)