...and ultra high velocity single human person agent swarm vibe coded replacements for existing software and SaaS should come out en masse. Where are they?
You seem to be arguing that vibecoding photoshop wasn't possible up until 2 months ago, with GPT 5.4/5.5.
That's a very, very weird take on many, many levels. Could you elaborate a bit about where that view came from, how often you use AI, what's your career etc.?
Before Codex with GPT 5.4 and 5.5 I was working on a single feature only, no parallel conversations, and a ton of permission prompts would make it impossible for the agent to even work for five minutes on its own.
I am working like 20 hours a week on my new iOS app with Codex.
People on here talk like it was some belief or suggest I am somehow profiting from "hyping" AI.
Is it so hard to believe that agentic coding now works? Engineers are taking it up left and right.
Edit with reply: I can't, because the app is still in the works. Also my HN account is again rate limited and I won't be able to post more comments.
Edit number two to the other comment:
It's not really that expensive. With Anthropic it would be $200, with Codex the $100 subscription is sufficient.
It is interesting phrasing when you say that the providers "are making me think" the use of their service would be better, rather than me reaching this conclusion myself after using their services extensively for my work.
And honestly, I think I've had it with HN. I can't even participate properly in the discussion, maybe because some moderator thought my comments and opinions unworthy again.
I recently had a coworker open my eyes to why vibe coding, or AI-assisted coding is so popular. He likened it to a slot machine, where pulling the slot's arm is like asking an LLM to code something. You get crap most of the time, but when it works, it's like getting a payout. That dopamine hit keeps them pulling, hoping for another hit, and they then believe it's a better way to develop software.
Hey, rate limits are incredibly frustrating, but contributing to HN is worth it. Try writing a polite, brief email to hn@ycombinator.com with a link to your user profile. Tell them that you’ve re-read the HN guidelines (https://news.ycombinator.com/newsguidelines.html) and that you’re willing to follow them. Then ask if it would be possible for the rate limit to be removed.
My gut reaction looking over your account is that you mean well but get a little heated. For example https://news.ycombinator.com/item?id=48147587 responds to no one in particular and calls HN drivel. Don’t do that. Thoughts like that are normal, but expressing them is difficult to do in a substantive way. It’s often better to not say anything if you feel yourself getting upset. (There are plenty of exceptions to this, but you have to do it in a way where you’re writing for the audience here, not for yourself.)
I think if you really put your mind to it, you can write substantively and stay off the rate limit list. Good luck.
But I don't think I'm going to email the mods and beg them to remove me from some list they added me to without notifying me.
I don’t feel like apologizing for complaining about the drivel some write because they don't like LLMs.
It was not my most substantial or productive comment, but I feel it is fair enough and did not target anyone in particular.
Contributing to HN is not worth it.
I'm spending my time, compromising my privacy, and advising potential competitors on what works best in my workflow. It's often not appreciated, so I might as well stop commenting so much.
> People on here talk like it was some belief or suggest I am somehow profiting from "hyping" AI.
Not really, the "people on here" rather consider that Anthropic and co. are profiting from you by making you think it's better to give them money to develop your app rather than do it yourself or hire a developer. The hype is there to steer you towards AI.
20 hours a week must be quite expensive in tokens.
"I am 100x productive with AI, I can ship in days what took months before" and "oh no, you don't understand, it's not really possible to vibecode Photoshop" found elsewhere in this thread.
If I were magically 100x productive, the first thing I would do would be to recreate Photoshop.
Do you use Photoshop? The underlying engine which gives support for layers and smart objects is in itself such an amazing piece of tech that nobody seems to get even close to (and I’ve tried them all).
The brush engine is fantastic, liquify and the general support for plugins, and heck, just the basic math behind the filters.
Canva and Figma are layout tools, not for pixel editing.
Recreating it would make it faster and cheaper, something that has been driving software for decades.
I'm not being argumentative; I was genuinely trying to understand why you would aim to recreate Photoshop in particular, because Photoshop includes such a huge range of functionality. If it's about recreating the brush engine, that's pretty achievable. I would be curious to learn why Krita is not enough though.
Context: I've developed multiple Photoshop file format parsers/writers and know Photoshop at a very deep level. And would never want to replicate the specific set of tradeoffs Adobe made in the 1980s.
That’s fair, it’s just that a lot of the functionality overlaps in very rewarding ways, even if you only use the overlap 5% it’s incredibly frustrating to not have that function when you need it
There is nothing close to Photoshop (or the Affinity suite) that runs natively on Linux. Despite how niche that market is, one could make big bank if they could magically create a valid alternative out of thin air. I’d pay hundreds of dollars for it myself. I don’t even care about PSD compatibility.
Okay, well there's a huge difference between Photoshop and Affinity, because Affinity includes an Illustrator and InDesign alternative as well.
What specifically do you need to do in Photoshop? Photo editing? Design? Illustration? It sounds like you have a concrete need if you're willing to part with hundreds of dollars. I've developed a number of graphics apps over the years, so my interest is not academic.
So how long do we have to wait? The reality is the actual output doesn’t match the hype at all.
Software engineers should be getting laid off all over the place, there should be a decrease in hiring period. This is not what’s happening.