TT

Demo of Lofi - a FREE wireframing tool. I’d love to hear your feedback! 🙂 No sign-up required, and your data is saved locally on your computer. Link in comment

@ryolu_ Just want to click on UI and edit like Figma 🙏

Agents that ask back, streamlined code reviews, faster grep, plus a bunch of polish – only in Cursor 2.1

@ryolu_ Just curious, why there's no auto complete/tab mode on the @cursor_ai chat panel?

@EvanDweck @desmondhth Genuinely curious. What research ?

The problem is the way the brain learns language is implicit vs explicit. There’s a lot of published research on this, just the gamified dopamine rush is really what they’re selling vs the outcome of improving fluency. If you want to learn a language you need to immerse yourself. It’s not an easy or fast, but it works.

when will people realise Duolingo is not a language learning app?

@ridd_design Yes please

wow just saw a prettttty compelling demo for a new way that designers can prototype on top of production 👀 it's kinda in stealth now but if you're obsessed with prototyping and want to try it drop a comment I'm just going to send this tweet link to the founders as a billboard

@ryolu_ @usgraphics That form tho 😍

Cursor CLI x @usgraphics is such a vibe ⬢ some close ups:

@ryolu_ @cursor_ai This GTP 5 support cursor todos ?

GPT-5 is here. It’s first model that I don’t ever think of switching. Available for free in @cursor_ai this week, and it’s smarter, faster, cheaper than previous SOTA coding models. …and we have one more thing ⬢

Since the AI model doesn’t know how to build good components with my system, I need to create an engine that lets me build components manually. Something like Figma could work. I decided to use the most expensive model, Claude Opus 4. I don’t have time to mess around, so the cost justified the time. I gave it a simple prompt: “Research the Figma components and variants, then see how you can implement a similar system for our app. No code, just a report.” I reviewed the report, adjusted things like where components should live, and simplified the scope. I gave it no UI or UX direction, mostly because I was lazy, but also because I was curious to see what a very expensive model would come up with on its own. I built a basic component system in about 15 minutes. If you’re wondering what UX quality the most cutting-edge model can produce without guidance, here’s your answer: it looks like shit. So, designers, you can keep your jobs for now. UX doesn’t matter that much at this stage. What matters is that the code is in the right place and the foundation is solid. From here, I’ll just keep shaping it. Design feels a lot like sculpting to me these days.

To start the build, I wanted to try something different: getting different AI models to pitch me solutions. I copied and pasted this post for context and told the models I’d go with whoever gave me the best answer. I tried three models: Grok 4: This model understood the pitch best and worked the hardest. But it only expanded on my thinking. It didn’t bring any new or great ideas to the table. Sonnet 4: It didn’t try very hard. It just built on my thoughts and suggested practical ways to implement what I already had. Nothing new here either. OpenAI o3: This one didn’t even try. Total nothing burger. I ended up going with a recommendation from Grok 4, take a premade system (Shadcn), parse it into LoFi’s JSON format, and build on top of that. I gave Grok 4 the job. I did a pretty bad job parsing the components though, so I scrapped the build and started over with another model. I tried Sonnet 4 again. It failed too. I’ve concluded that these AI models are struggling because they aren’t familiar with LoFi’s layout system. They don’t know what 'good' looks like, so they can’t automate the process properly. I’ll have to manually create a few solid examples first, then try automation again later. I need a new solution.

Build Log 1: I’m kicking off my next big feature for LoFi: the component system. While looking for inspiration, it feels like Figma’s system is still the only game in town. But to be honest, I’ve never liked how Figma handles components. Here’s why: 1. It makes the user work too hard Take the humble Button component, probably one of the most standardised elements in any UI. Sure, the style and behaviour might vary slightly by platform, but 90% of the time it’s the same. So why make me build it from scratch? You could argue Figma’s system is flexible for customisation, and sure, it is. But software isn’t plastic. You can offer full flexibility and ship components like buttons and forms with smart defaults and customisable options out of the box. 2. Too many dropdowns and toggles The way we customise components is through toggles, dropdowns, nested panels, feels like a solved problem that no one’s bothered to rethink. What if components were context-aware and adapted to the environment they’re placed in? This is a hard problem to solve. I’ll need to get back to you on that one. 3. Figma components are built for UI/Dev, not for design thinking Figma’s components focus on structure,size, states. But they ignore design intent. They don’t help you answer: What makes a button convert better? What tone or language should I use here? When should I use urgency? How should I pair buttons to guide decisions? None of that is baked into the system. But it could be. --- The Challenge So yeah, the goal is to build a better system than Figma’s. No pressure. I’ve given myself 2-3 weeks to ship it. Can I pull off something creative? Honestly, I don’t know. This shit looks hard. If you’ve got any ideas, throw them my way. I’m starting from zero here. lol.

🚢 Shipping new feature this week: AUTO LAYOUT. Took about a week, a lot of swearing, and not much sleep. Wouldn’t recommend building it urself.

Demo of Lofi - a FREE wireframing tool. I’d love to hear your feedback! 🙂 No sign-up required, and your data is saved locally on your computer. Link in comment

Hi, I’ve been building this FREE wireframing tool every night while my kids are asleep. If you need a simple app to make wireframes, please check it out, more to come, feedback welcome :) lofi-design.com

🚀 I launched a FREE thing, thanks! lofi-design.com

I'm launching a FREE wireframing and ideation tool soon. Do you like the bottom toolbar?

@yacineMTB When is @elon going to buy them ?

I don't think you understand How hard they cooked

@Vinod_r108 @nocapmedia Plot twist. The guy is the dad!

@nocapmedia What would you do in this situation?

Ain’t no way 😭😭😭😭

MagicBook is the most fun way to create AI illustrations. It’s inspired by the charm of scrapbooking, hands-on, personal, and a little imperfect. I could automate everything, but I believe there’s magic in putting together something yourself.

@OfficialLoganK Can you please buy @midjourney so we can have that API. That's what the world wants! Thank you.