@thsottiaux Can we get some clarity on the "Selected model is at capacity" problem myself and many other Pro 20x users are encountering? I'm about ready to jump ship to another provider
https://t.co/5NWXsl9KhP
@thsottiaux Hi, I am unable to access my ChatGPT account (Pro 20x). I get this error when opening the desktop app. I was messing around with cliproxyapi and I fear that it may have gotten me flagged. Is there anything that can be done? Or can I at least refund the remainder?
@poteto How do you recommend using pstack for orchestration? I had some success running the orchestrate playbook against my backlog, but I was wondering if you had any tips on how to get the most out of pstack
@poteto pstack is wonderful, thank you for building it! I often forget to mention my project's verify skill in my prompts. What do you think of letting /poteto-mode discover & route to the project verify skill when appropriate?
@thsottiaux I also tried to solve it myself by routing GitHub events to ChatGPT Desktop using the App Server, but I ran into problems getting the chat UI to update when it takes a turn in response to an event.
https://t.co/VVk6ZRERba
@thsottiaux When working on coding tasks, the one thing I miss most from Claude Desktop is their "Auto-fix CI and address comments" toggle. Is there an equivalent feature or pattern in ChatGPT Desktop I am missing? I am currently using /goal with a skill for finishing PRs, but it's not great
The CEO of Take-Two, the company behind GTA, just said something the entire AI industry doesn't want to hear.
And he said it without being anti-AI.
Strauss Zelnick's argument is precise. AI is built on datasets. Datasets are backward-looking. Creativity is forward-looking. A model trained on everything that already exists cannot, by definition, produce something genuinely unexpected. And all hits, by their very nature, are unexpected.
Asset creation and hit creation are not the same thing. AI is getting very good at the first one. The second one is what actually makes money, builds franchises, and changes culture. Nobody has shown AI can do that yet.
The derivative property problem is real. You can clone GTA with existing technology. You could do it before AI. It would take 3 years and look identical. It still wouldn't sell. Because it isn't GTA. It's a clone of GTA.
And consumers, despite what the industry occasionally pretends, can feel the difference between something genuinely new and something assembled from the residue of things that already worked.
Thousands of mobile games ship every year. 0 to 5 hits get made. The same studios make them every time. The technology to make more games has been commoditized for years. It didn't democratize hit creation. It just flooded the market with more forgettable product.
The Silicon Valley thesis that AI unlocks game creation for everyone is true in the same way that cheap cameras unlocked filmmaking for everyone. They did. And the same 5 studios still make the movies everyone watches.
What Zelnick is saying, without quite saying it, is that the thing AI cannot replicate is taste. The instinct for what hasn't been done yet. The cultural antenna that detects the gap in the market before the data can see it.
Data tells you what people wanted. Hits tell people what they want next.
Those are different jobs.
@kentcdodds We use MUI on a smaller application. Their docs serve our UX folks well on what UI components are available to use. Maintaining our own Storybook cost too much developer time for the value it was giving us. We are open to revisiting it in the future as our team and app grows.
Exploring ATX for 3 days! π€
π @patinaproject.app feature (swipe left): Photo grid view for your boot collection and the @stitchdownpatinathunderdome. We hope this helps you find interesting boots! π₯Ύ https://t.co/sHvtCiTALK
Knocking out some late night @patinaproject.app bugs! We truly appreciate the rapid feedback. ππͺ²π¨ #patinaproject @ Carrollton Station https://t.co/EARWW8HC1p
Custom 6β Role Club Tanker boot. Overdyed black Steerhide. Shoelast 100. RC full soles and heels. Low block heel. Black edge finish. #roleclub#tankerboot#vintageinspired