Live data from Hacker News

Viewing profile — jjcm

jjcm

HN member
Joined
Fri, Aug 13, 2010, 10:07 AM UTC
HN karma
11,254
Public activity
1,520 items

About jjcm

Jacob Miller

Working on diffui.ai - diffusion for UI design.

Formerly Figma, Atlassian, and Microsoft.

AMA about design tokens, webcomponents, and design systems!

+1 808 366 1708 j@jjcm.org

Recent public activity

  1. comment
    Comment #49206698

    to be fair, it's running an 8b model from like 2 years ago. Taalas just does the chip design, not the model architecture.

  2. comment
    Comment #49202580

    China has caught up is the main takeaway here. The SOTA models are so close that it's really hard to compare them intelligence wise - you have to get a feel for them yourself and w…

  3. comment
    Comment #49190465

    That's a fair perspective of before/after. And yea, possibly this was just me curating my feed to a point where it's kind/pleasant. It truly is though - mine is free from politics …

  4. comment
    Comment #49190444

    > The only way to prevent your tweets from being recommended to random people is to lock your account, and that makes it pointless to reply to people who don't follow you or to lik…

  5. comment
    Comment #49190128

    I actually really like that pricing strategy. It's very transparent

  6. comment
    Comment #49190079

    There's a lot of negative about twitter here, especially related to timeline being shit. I'd like to give a different perspective - it's an algorithmic feed like anything else, it …

  7. comment
    Comment #49187512

    Yea, the prompt was the expanded json the diffui harness uses. And re grabbing the designs, go for it. I expaneded out the designs here - feel free to copy them for your agent to b…

  8. comment
    Comment #49186993

    It's wild how much these agent interfaces have aligned UI-wise. There's almost zero difference between all of them.

  9. comment
    Comment #49186965

    I was playing with this a bunch when it dropped a week ago. It's a big step up over their prior model, but it's nowhere near gpt-image-2 at least for high density UI design. Photos…

  10. comment
    Comment #49152450

    Also tried Qwen Code. Tried it with a coding plan and it 401'd. Tried it with an api key I loaded up with pay-as-you-go credits and it 401'd. It did a self update and it worked for…

  11. comment
    Comment #49152369

    Update: Tried using Qwen Desktop. It told me it succeeded, and linked me to the folder it created it in. That folder didn't exist, I asked Qwen where the files were, and it attempt…

  12. comment
    Comment #49151983

    The visual web development / perceptionbench scores are very promising for image->html flows. Here are some test results. Original designs: https://image.non.io/257dc9cb-9e6b-4e00-…

  13. comment
    Comment #49139765

    The quality is quite high, but an observation is the direction they're taking these models correlates heavily to the usage demand of China vs the West. Specifically, they're immens…

  14. comment
    Comment #49118518

    Oof, apologies. I have not done any work at all on mobile to make this work.

  15. comment
    Comment #49118516

    You have my dota 2 aus guild beat by a couple of places: https://image.non.io/dad602c8-4774-47dc-b671-c515c67a0cf1.we... You definitely can do fun/creative things with LLMs, but th…

  16. comment
    Comment #49117968

    ty ty, though I do agree with azan that the imagery inside of it looks generated (as it is). That was really a test of whether or not newer models could implement box shapes that a…

  17. comment
    Comment #49117951

    I think it's important to separate patterns from aesthetics. Patterns help us understand a new interface for sure, but aligned aethetics start to look mundane. That's why I was spe…

  18. comment
    Comment #49117925

    Yea. I have a very speed run version of how I made that one here: https://x.com/pwnies/status/2076755344471289898 But basically diffui's build step provides an API to create normal…

  19. comment
    Comment #49117891

    A few layers to it. When you prompt on my product I expand out that prompt into a semantic json blob that represents the style, theme, color palette, and subjects on the screen. I …

  20. comment
    Comment #49117868

    Ha! Totally fair. 13 cents is 0% margin, which is what I'm targeting for individual plans. I literally just got my SOC2 compliance complete an hour ago, and I'm gonna roll out team…

  21. comment
    Comment #49117565

    > There are other aesthetics my brain associates with AI, like beige/cream colors, orange accents, and serif typefaces Something to consider regarding the narrow space AI-created d…

  22. comment
    Comment #49114129

    > every pen is deployable It will be interesting seeing how this evolves. Any free hosting solution tends to spiral towards abuse at some point. Still trying to solve it for my own…

  23. comment
    Comment #49093738

    Yo that homepage zoom from the app screenshot straight into the experience was SMOOTH.

  24. comment
    Comment #49077046

    > > All sufficiently capable models, open and closed, should go through mandatory safety testing. The problem with this is the cycles required to abliterate a model is significantl…

  25. comment
    Comment #49044147

    This is my own tool, diffui. Thanks, though I will say I spent like... 7 minutes on this. Feel free to completely lift the design or the implementation.