← Back to context

Comment by weli

1 day ago

Anecdotal, opinion:

Gpt is really good in vision stuff, or at least their MoE seems to be really cohesive. From my experience Claude models can be really good at language but the moment they need to look at a picture and decide why the design is not good what parts need improvement it degrades a lot. My easiest benchmark is giving them a screenshot of a feature in my app and tell it "identify non-normative UI blocks and improve readability and consistency". Sol does a great job at re-structuring the page into composable units that build upon each other and the general looks and feels of the app. Claude tends to over-focus one one part while completely forgetting about the rest or the cohesion as a whole.

16 comments

weli

Reply
velcrovan  1 day ago

Assessing the subjective quality of a thing is in my experience one of the worst ways to use any LLM.

  • TeMPOraL  19 hours ago

    There's a lot of objective principles and decisions that go into subjective quality; if you don't know the field well, asking LLM for assessment is a good way to discover all that.

  • rib3ye  1 day ago

    anthropic frontend-design skill does a great job with it.

    • DaiPlusPlus  1 day ago

      My exposure to Claude-produced UIs is limited, but I have started to notice certain design trends they tend to have in-common, which might be becoming hallmarks of AI-produced UIs - the same way we've started noticing the clichés of low-effort LLM-generated text.

      FWIW, the summary-description[1] of "frontend-design"[2] gives me a few things to pick at:

      > create polished code

      Methinks only if you're using it with a very popular framework like React. What happens if you ask Claude to make the UI in WinForms or MFC?

      > high-impact animations

      That's bad UX 101 right there: animations in a UI exist as an affordance to the user, and never for its own sake (e.g. macOS's "genie" animation when you minimize a window to the dock exists so the user knows where they can restore the window from). The only people who actually want "high impact animations" in software are salespeople who want something for demo purposes.

      > generic system fonts, predictable purple gradients, and cookie-cutter components.

      This screams wanting to be different for the sake of standing-out, not because it results in a better software product; users benefit when their software fits-in with platform conventions: if you refuse to use a stock checkbox <input> or <select> drop-down and instead use your own entirely custom component solely for aesthetic reasons then you are producing worse software. There's nothing wrong with system-fonts, but your site will look ugly after your third-party font-host CDN shuts-down and turns into a walking CSRF factory.

      > thoughtful typography with unexpected font pairings

      The above fragment set my alarm-bells off. Yikes.

      > scroll-triggered interactions

      Not every web-page should be an Apple.com product brochure page. This is also a fantastic way to make your webpage horribly inaccessible.

      ------

      The SKILL.md itself[3] grinds my gears too:

      > Approach this as the design lead at a small studio known for giving every client a visual identity that could not be mistaken for anyone else's.

      Claude has no way of knowing what designs are actually unique or not...

      > For web designs, the hero is a thesis. Open with the most characteristic thing in the subject's world, in whatever form makes sense for it: a headline, an image, an animation, a live demo, an interactive moment

      ...this is exactly what everyone else's web-pages look like!

      > For calibration: AI-generated design right now clusters around three looks: (1) a warm cream background (near #F4F1EA) with a high-contrast serif display and a terracotta accent; (2) a near-black background with a single bright acid-green or vermilion accent; (3) a broadsheet-style layout with hairline rules, zero border-radius, and dense newspaper-like columns

      ...I called this out weeks ago[4], lol.

      and I could go on. This is all quite painful to read.

      ------

      [1] https://news.ycombinator.com/item?id=49187385

  • keeganpoppen  17 hours ago

    i'd say this is something that has gotten orders of magnitude better with recent releases than it used to be, fwiw

SkalskiP  21 hours ago

Hi! I’m the author of this blog. GPT-5.6 is much better at vision than previous GPT versions, but it’s still much weaker than Gemini 3.5 Flash or Gemini 3.7 Flash, which was released last week. One interesting approach is to use Gemini through a tool call.