That's a really useful distinction to have explicitly articulated. It's also why plan mode feels like a super power. Research vs Generative AI are different: I'm going to use this.

your paragraph is parent's point in action.

If only all great works could just be an X post!

> what if you don't give a shit about design and it's a means to an end…

the parent's point is that it doesn't work that way. The point is self reinforcing. Design is not a thing. it's the earned scars from the process. Fine to disagree but it reinforces the point.

related: Cursor composer line of models is so good relative to cost. "auto" served me just fine until they recommended Composer and I've been continually happy with it. Then Claude Code with Opus dropped and everyone went bananas and I gotta say I just assumed I'm too casual to know how bad Cursor has been?

But then I think maybe not really? Granted, I'm not orchestrating 100 Agents doing overnight work. But relating this to your point, if the CC-camp + HN hadn't proclaimed otherwise, I would have no idea what breakthrough CC+Opus made. (Cursor was first with plan mode right?)

I don't think Cursor was _that bad_ in it's time. But the 'psyop' here is that anyone is using an AI-IDE going forward at all. I see people who say they are still using them and are so excited, but then I talk to engineers I actually know and it's all CLI tools.

FWIW, cursor (company) has a CLI tool/harness similar to Claude Code called agent.

It’s existed for a long time, is quite good, and it is under-marketed (ironic for this thread).

(Double-ironic disclosure… I work for Cursor. If you have ideas to make agent better hmu)

> I don't think Cursor was _that bad_ in it's time. But the 'psyop' here is that anyone is using an AI-IDE going forward at all. I see people who say they are still using them and are so excited, but then I talk to engineers I actually know and it's all CLI tools.

This is just the old "surely nobody actually likes Lady Gaga, all the people I actually know think her stuff sucks, it's just all bought and paid for" reasoning trap all over again...

You couldn't even keep your analogy straight. I didn't say the people I know said anything at all about Cursor.

If someone is clear about offering an anecdote, it's dishonest to pretend as if they were making a real and reasoned argument.

I haven't used Cursor much lately, but with Opus/Codex I can program with very few bugs without having to look at any code at all, over months of working on the same codebase. I don't think any other model can do that, no?

In Cursor I look at the code diff for my own satisfaction and understanding. I've been able to auto-accept all changes pretty reliably all last year.

So much so that i've yet to invest in CC. Finally downloaded the desktop app but use it exclusively for chat and cowork.

Cursor's purgatory UX is what'll finally get me to invest in CC and codex. Not model performance.

I do think there's a caveat that it's pretty standard nextjs with rails api.

edit: found your blog post about your experience, i'll read it! https://www.stavros.io/posts/how-i-write-software-with-llms/

edit2: maybe it's because i spend a lot of time being clear with small and surgical asks after doing purely thought exploring prompts to confirm and home in on approaches. At the point I hit build or do Agent mode, Composer is mostly always spot on.

with Opus (haven't tried) maybe people are doing large-scale multi phase and single shot prompts that trigger a swarm of sub agents?

you must never have actually done this. it doesn't work the way you think it does. unless it's self contained (like a pp), you can't expect network access to actually deliver when you need it most.

The file the Claude skill spits out is actually fully self-contained, no network access is needed.

that's pretty cool!

you could do that for the past 20 years. i've always hated slides as a medium for anything, but i've been proven wrong tine and again that people love their pp.

Because it was drag and drop interface. This existed for HTML but because web pages got too complicated, so did the WYSIWYGs. By just being a program to show slides, the editing experience was manageable for anyone. But if you can hust type what you want to happen into claude, editng experience doesnt matter as much/at all

Many people are trying to make this thing, this is the one we can all see. I'd rather have the visible one remain visible because it gives us a useful data point and/or entertainment.

fair

I think the talking point is maintaining a well versioned and solid API as product is way harder than shipping a few screens that can change whenever you need them to. (behind those screens being a bunch of duct tape to a clusterF of internal APIs). no guarantees.

what you're saying is that you were at a company that did that hard thing of shipping APIs as product.

the url for your company in your profile is misspelled.

Ty fixed! Allow me to blame it on the lack of sleep as I'm in the current yc batch.

Good luck! The premise sticks immediately.

If attention-span was shot with social-media, it has no chance in the age of AI. All these deep tech-tools potentially have tons of value, but if it doesn't make sense in 5 seconds, very hard to compete.

Surprised this is your take coming from a UX designer. You think a straight path for every user to add their feature ideas results in a good UX?

edit: reading further into this, the idea is perhaps that users vibe-code their own distinct UX with everything valuable to them. That's not a bad take, but even in that world, I wouldn't think UX and product disciplines become exposed for having no value at all.

My take in this (ironic) comment was just "no feature is free", which I don't think should be odd coming from a UX designer!

> the idea is perhaps that users vibe-code their own distinct UX with everything valuable to them

I do find this interesting. I work on a complex business operations and reporting platform and every facility has their own lil quirks. More control in their hands would let them smooth out their workflows while still relying on the foundational work our platform does.

Ah, I didn't register the sarcasm. Typical HN, it's probably why you're downvoted.

Yes, today's HN session has me nerd-sniped about what the future of product development looks like. I've been thinking how mock-to-prototype is just too slow when engineers can ship so much so fast. Eng needs design direction especially when it's too easy to "solve design" with tailwind components and "You're a designer from a top saas company" prompts.

But what if the new UX is less visual-first and more IA, primitives and well structured object models... now that has me thinking.