The dangers are obvious (and also there are some fascinating insights into how healthcare works practically in China). I wonder if some kind of "second opinion" antagonistic approach might reduce the risks.
Medical Advice Generative Adversarial Networks would be a good idea.
I see some of this adversarial second-guessing introspection from Claude sometimes. ("But wait. I just said x y and z, but that's inconsistent with this other thing. Let me rethink that.")
Sometimes when I get the sense that an LLM is too sycophantic, I'll instruct it to steelman the counter-argument, then assess the persuasiveness of that counter-argument. It helps.
I hadn't really even seen much in the way of recent, first / second person accounts of what it's like to receive chronic care in modern China. It's sad but maybe not surprising to see that it's dysfunctional in its own special way.
torstenvl|1 month ago
I see some of this adversarial second-guessing introspection from Claude sometimes. ("But wait. I just said x y and z, but that's inconsistent with this other thing. Let me rethink that.")
Sometimes when I get the sense that an LLM is too sycophantic, I'll instruct it to steelman the counter-argument, then assess the persuasiveness of that counter-argument. It helps.
cassepipe|1 month ago
blacksmith_tb|1 month ago