I built this medical diagnosis simulator (`chat-a-cold.html`) in just 3 hours.
The interesting part is that I didn't "code" the medical logic in Python or C++. Instead, I used a methodology I call *NLCS (Natural Language Constraint System)*.
I simply defined the "thinking structure" of a doctor (Input -> Criteria -> Exception -> Output) in natural language, and the LLM executed it as a game engine.
* *Logic:* Differentiates between Common Cold (90%) and Sinusitis (10%) using hidden variable checks.
* *Cost:* Near zero development cost (just prompt engineering + structure design).
* *Result:* It simulates an intern's diagnostic process with high accuracy.
The repository includes the full whitepaper (PDF) and the runnable HTML file. I believe this demonstrates that "Cognitive Architecture" is more important than raw knowledge in the AI era.
Of course they did, they are sycophants
They will tell you any idea is a great idea. It has no bearing on the actual "goodness" of an idea
https://www.seangoedecke.com/ai-sycophancy/ (currently on the front of HN)
> the LLM executed it as a game engine
Did it? How did you verify?
How do you know it's not just telling you it did something without actually doing it?
reply