Tier 1/2 typically has greater access to systems than humans do. They can operate in ways that AI agents just don't have access to, maybe for good reasons.
For example, I lost my debit card while traveling. Only an agent could route the card to my hotel.
Even the example apps in the post seemed like AI slop to me. Common markers are too noisy/busy (mainly repeated or rephrased information). Text being a bit too big (Codex-only?).
Yes in my experience, AI designs might look okay on first glance but when you really start to look you start to see strange and inconsistent things. Similar to looking at generated code.
You can have it fix these things. It has the tools to analyze screenshots of the app and correct things like formating, alignment, color, etc.
I've been building a personal app with Opus 4.8 over the past two weeks and the design is excellent. I provided it with screenshots of what I wanted, then had it build out a gallery of functional UI elements (like designers do). Claude built out a tool that would screenshot the app, compare it to the design screenshot and automatically reposition elements or update the styles to match.
You can also provide it with a style guideline prompt and have it double check all the work it produced matches the UI style guidelines before committing.
This article feels is trying to justify their own inefficiencies (lack of library or language knowledge) instead of taking the time to learn from the rockstar and their technology choices.
As I was leaving my last job, I advocated everyone migrate from plain old es6 to typescript, b/c several times broken builds made it to production.
Certainly my coworkers may of felt upset that typescript is too verbose and pointless if everyone reaches for the "any" operator. But that doesn't mean the decision to move to Typescript was bad, it just means the company is "old school" and not willing to take the time to adopt modern workflows...
I don’t know the leak, but I had someone take out multiple credit cards by phones on loan with my Social Security card. I had to freeze my credit score on all the providers (which I think is ridiculous that I have to like. Tell another company that I didn’t even sign up for to pause the account that they created for me)
And then go to each company and bag them to except that this was a fraudulent situation and not me. If they didn’t accept my request, then I would basically be out of luck, owing them the money.
These data leaks are great opportunities for doxing. You can look up all the people that have died from swatters.
Do you have any like dyes or work clothes describing this process?
I don’t know what prompted to get it away from the base model and any of like the non-standard web design like styles are a little bit too harsh for me if that makes sense. Like for example I like brutalist design, but it just feels heavy sometimes on the apps that I’m making.
I’ve tried to get the AI to describe a style based on the product name or you know it seem that I wanna have for example travel. But then it creates us like steal, amorphic design where everything looks like a boarding pass airplane ticket.
I don't think AI introduces anything new. In theory, manager could pull the reports of their 4-12 people to see which programs are active and what websites they are using for how long once a month, targeting individuals that they are looking for a reason to bump. No AI needed.
Tier 1/2 typically has greater access to systems than humans do. They can operate in ways that AI agents just don't have access to, maybe for good reasons.
For example, I lost my debit card while traveling. Only an agent could route the card to my hotel.
reply