While the "5 Whys" technique is a terrible interrogation technique for UX research, it seems surprisingly effective with LLMs. It made the model realize what it had messed up and correct itself. The 5 Whys were developed to determine the root cause of production line defects at Toyota factories. Fitting for what we do with models today.
As long as design represents quality, how fast we ship cannot be its measure.
Design also means creative experimentation.
You try something, see what happens, change your mind and try again.
We have more time to explore further, instead of expecting an earlier finish every time.
People shipped "fast" before LLMs came and sometimes they shipped without any user research or a dedicated designer: optimizing for quality is not new.
Faster tools are a chance to use more creativity and make better things if the designer has time to do so.
"Report" is my all-time favorite comic strip. I have it framed on my wall. I just went by it and thought how relevant this one has became lately...
(Poorly Drawn Lines, 2018)
Fable 5 vs. Fable 5.1 for AI 3D generation.
Same task: one-shot animation of a low-poly German Shepherd.
Fable 5 took me many iterations to get right. 5.1 has a serious head start. w/ Claude Design.
Fable 5 vs. Fable 5.1 for AI 3D generation.
Same task: one-shot animation of a low-poly German Shepherd.
Fable 5 took me many iterations to get right. 5.1 has a serious head start. w/ Claude Design.
With LLMs, designers started to ship front-end. That is where much of accessibility actually needs to be handled, not in Figma prototypes where color, contrast and size mostly cover it on a static canvas.
Keyboard use, focus, semantics, screen readers, motion, zoom and actual interface behaviour are now part of our daily practice.
Surprisingly, I don't see LLMs generating accessible interfaces by default. You would think standards are the kind of things machines should be good at following. Relying on 3rd-party Skills feels like patchwork. At least, LLMs are good at pointing out what is missing, so you can do the job for them.
@DiegoTalksAi@itsolelehmann People overestimate Obsidian in the stack. Think it's because the graph view. You can generate a better, custom graph tool with an LLM.
Been working on a Design Systems LLM logic for existing products for the last few weeks. It takes a lot of hands on work. One of the TLDR results is: the "design.md" magic does NOT work. No one shot Skill is feasible. Don't trust them, use as inspiration only.
43% of designers spend more than half their time vibe coding.
37% do zero.
I just finished going through 1,478 survey responses for our State of Prototyping report.
Designers spending about half their time vibe coding is the smallest group at 12%.
People aren't easing in. They're either all-in or they haven't started.
Design engineers make up 80.9% majority vibe coding.
IC designers: 35.0%.
Workflow satisfaction tracks with them:
- No vibe coding: 5.93/10
- Heavy vibe coders: 7.39/10
Full report, raw dataset, and open API available thanks to @dazl_dev, @framer, @MagicPathAI, @dscout, @magicpatterns, and @mobbin.
@designertom Thank you for this, well put. I was always drawn to game design. I ended up in UX, but now I can finally start experimenting. Lower rev is fine with lower costs. Niche target groups could be served.
Watching @Claude making annotations on my web app in real time is rewarding and a little deceptive.
Opens browser, scrolls through everything, clicks on
elements, and writes design critique annotations directly on the UI.
Stack: Agentation (by @benjitaylor) + agent-browser (headed browser CLI) + Claude Code skill.
Made 15 annotations on my new university tool: broken visual hierarchy, misleading empty states, competing with CTAs... and fixed all 11 in one pass.
Super useful, but Claude still misses deeper issues around value proposition and user flow (this was made with gstack, btw). Senior UX designers are still very much needed to orchestrate this.
@CiaoQuirkTax Haha, true π I wasnβt active here. Mostly reading, follow all kinds of creators to catch all the resources, tools I can try. Managing my lists is a challenge.
I built a Claude Code skill to fight "Brain Fry" (more decision fatigue, more errors from managing AI threads).
Every unclosed terminal session is an open loop you're tracking in your head.
/close is a ritual that gives AI sessions a definite ending: