Live data from Hacker News

Viewing profile — seanw265

seanw265

HN member
Joined
Thu, Sep 29, 2022, 5:14 PM UTC
HN karma
163
Public activity
61 items

About seanw265

building Easel @ https://tryeasel.dev

bsky.app/profile/seandubb.com

Recent public activity

  1. comment
    Comment #47890565

    I take some issue with that testing methodology. It seems to me that you're conflating the model's performance with the reliability of whatever provider you're using to run the ben…

  2. comment
    Comment #47839388

    Kimi K2.6 also released today. I think it's fair to compare the two models. Qwen appears to be much more expensive: - Qwen : $1.3 in / $7.8 out - Kimi : $0.95 in / $4 out -- The an…

  3. comment
    Comment #46531522

    I'll piggyback on this to highlight Refactoring UI as well. It's an ebook by Adam and Steve, though I'm not sure if it's technically part of Tailwind Labs or not. This book taught …

  4. comment
    Comment #46327610

    It's always up to the reader to determine which biases they themself care about. If you're wondering at what point "we" as a collective will stop caring about a bias or set of bias…

  5. comment
    Comment #46275377

    I’d argue the goalposts have moved substantially over the past decade. The LLMs we casually use in ChatGPT today would have been described as AGI by many people 15, 10, maybe even …

  6. comment
    Comment #46218852

    This is not what the article says at all. The article is about the constraints of computation, scaling of current inference architecture, and economics. It is completely unrelated …

  7. comment
    Comment #46138262

    I tend to agree. Cloudflare and Vercel were able to mitigate in the form of WAF rules, but it's not immediately clear what a user or vendor can do to implement mitigations themselv…

  8. comment
    Comment #46113631

    FWIW it looks like OpenRouter's two providers for this model (one of whom being Deepseek itself) are only running the model around 28tps at the moment. https://openrouter.ai/deepse…

  9. comment
    Comment #46109670

    Thanks for the thoughtful reply. Best of luck!

  10. comment
    Comment #46109627

    After reading the post I kept thinking about two other pieces, and only later realized it was Taylor who had submitted it. His most recent essay [0] actually led me to the Commonco…

  11. comment
  12. comment
    Comment #46048643

    Stripe billing definitely leaves something to be desired and agree that a layer on top can improve the DX tremendously. What differentiates you from competitors like Lago and Autum…

  13. comment
    Comment #46048191

    If they are serious they should realize that "80% accuracy" is almost meaningless for this kind of classifier. They should publish a confusion matrix if they haven't already.

  14. comment
    Comment #46048025

    I haven’t tried it myself, but if you’re asking specifically about the human models, the article says they’re not generating raw meshes from scratch. They extract the skeleton, sha…

  15. comment
    Comment #45801999

    Aha! Now I see I'm talking to the expert on the topic ;) Thanks for the link. I'll check this out.

  16. comment
    Comment #45801700

    Doable for http and https, but if you're running it in a browser environment, you'll eventually run into issues with CORS and other protocols. To get around this you need a proxy s…

  17. comment
    Comment #45801155

    Very cool! I'm curious as to how it compares with WASIX in terms of both compatibility and performance. Also tangentially related: I'd love to see a performant build of Node.js com…

  18. comment
    Comment #45540276

    The designer obviously knows a thing or two. I enjoyed the fun presentation that others seem to dislike. Where I ran into trouble was the readability of the annotations on the visu…

  19. comment
    Comment #45539835

    I’ve got a random subdomain hosting a little internal tool. About twice a year, Google Safe Browsing decides it’s phishing and flags it. Sometimes they flag the whole domain for go…

  20. comment
    Comment #45528361

    I suspect you haven't tried a modern mid-to-large-LLM & Agent pair for writing code. They're quite capable, even if not suited for all tasks.

  21. comment
    Comment #45505414

    Living life on the edge, huh? Sometimes I notice myself go a bit too long without a commit and get nervous. Even if I'm in a deep flow state, I'd rather `commit -m "wip"` than have…

  22. comment
    Comment #45428799

    Very cool. I've spent quite some time working on compiling Nodejs for WASIX. Not an easy task. Would love to see this open sourced at some point.

  23. comment
    Comment #45425701

    If the agent only needs the filesystem then probably. If it needs to execute code then things get flaky. The WASM/WASI/WASIX ecosystem still has gaps (notably no nodejs).

  24. comment
    Comment #45425658

    Containers might be fine if you’re only sandboxing filesystem access, but once an agent is executing code, kernel-level escapes are a concern. You need at least a VM boundary (or s…

  25. comment
    Comment #45183719

    I'm still not sold on liquid glass as a whole. It can be quite beautiful, but in the demos provided (and even in Apple's promotional materials) I think readability of UI elements s…