Try 5.5 on xhigh, scope the prompt well, ask it to write tests first, run /goal mode till a) all tests are green and b) a sub-agent with a clean context window can test the API and it works perfectly Overkill for 99% of APIs but maybe yours is extremely complex?
@mattshumer_
-
Use loop prompt with Claude to perfect impossible tasks
By
–
I don’t usually get excited about Claude models at all. Look at my track record. When it comes back, try it on a task you feel is completely out of reach for modern AI. Use a /loop prompt that provides a way to verify the result, and tell it not to stop until it’s perfect.
-
Seedance 2.0, Hyperframes, Remotion with Claude for programmatic videos
By
–
Seedance 2.0 for pixel video generation, Hyperframes and Remotion with Claude models for programmatic videos.
-
Fable’s magic lies in tasks beyond other models’ capabilities
By
–
Seeing so many people saying Fable wasn’t that much better than other models. Sure, if you’re just doing normal frontend/backend work that Opus/GPT 5.5 can already do, it’s going to feel basically the same. The magic comes when you’re asking it to do things other models can’t.
-
Opus not good enough for 3D and verification
By
–
Opus is nowhere near good enough at 3D/verification. I’ve done some Opus ultracode runs and it’s passable, but not great!
-
Claude Code loop prompt and references for quality bar
By
–
Yep. Claude Code. Got this one in particular working really well with a loop prompt and a bunch of references to serve as the quality bar.
-
Claude Fable’s Pixar-quality video previews Alpha School AI education
By
–
Claude Fable made this Pixar-quality educational video in one shot.
— Matt Shumer (@mattshumer_) 15 juin 2026
It's a preview of what I'm doing next:
I've joined Alpha School to push the limits of what AI can do for learning.
We're going to transform education for 1B kids. pic.twitter.com/b936wcQQqMClaude Fable made this Pixar-quality educational video in one shot. It's a preview of what I'm doing next: I've joined Alpha School to push the limits of what AI can do for learning. We're going to transform education for 1B kids.
-
Not being paid for complex 3D tasks Opus cannot do
By
–
Not being paid. The tasks I was working on were things Opus just cannot do. If you’re just doing frontend development or something like that, yeah, it’s not that much better (Opus is already great!). But for more difficult problems (this week I was working on some 3D stuff),
-
Crosses long-horizon capability threshold like GPT-2 to GPT-3.5
By
–
It crossed a long-horizon-capability threshold that completely changes how you can use it. It’s like GPT-2 -> GPT-3.5
-
AI as leverage: the importance of knowing how to apply it
By
–
🙂 AI is leverage, just have to know how to apply it!