It's entirely unforgettable, isn't it? How many packages can we recall exactly from childhood? For me, it was nearly 50 years ago. It's a master class in branding.
I've also used iterative, interactive development for years and I agree, this is a big deal for Cursor.
It is interesting that it works with print debugging rather than breakpoints (as do I). It also points a way forward to finally be done with tools like Figma and Miro which can't roundtrip code; they only create artifacts for someone else to code up.
Each model is given the entire thread, so you can switch anytime. But they don't know who wrote what part and it's not important. The output text is predicted based on the entire contents of the thread and the system prompt says "I" for the LLM and "you" for the user regardless of which model is the "I" at the moment.
They don't "know" anything that isn't submitted as part of the prompt (ie: the context). I haven't heard of any vendor adding "model-aware" info to the system prompt such that they would know when you changed models, nor why that would be helpful.
Exactly. Most problems are due to Unclear Requirements before start of a new Project. Build one to throw away.
How do you think this changes with AI?
How? Even with all the intelligence AI cannot Architecture an entire product?
What changes are needed to make it autonomous and self refactoring?
reply