Hacker News Reader

Comment by frumplestlatz | Hacker News Reader

That sounds like a terrible use-case unless there’s already a pre-existing relationship with the provider, and it seems questionable even then.

View on HN

Clearly you've never had shitty insurance and a need for a doctor. I've spent multiple hours on the phone trying to find someone that takes my insurance. It's an actual problem.

It will be more of a problem if 100 idiotic startups are cold-calling doctors offices via their AI agents.

It’s already often difficult to get a human on the phone.

Sounds like the doc office should just list what they accept on their website then, god forbid.

It is absolutely a problem. One that will not be solved with LLMs.

I don't think the parent comment disagrees with it being a problem. I read it as more: the use of an agent doesn't resolve the ambiguity in the underlying problem but instead injects another variable that could further misrepresent whether the person has valid insurance coverage (e.g. hallucinating or misunderstanding the nature or extent of coverage).

I've spent multiple hours on the phone trying to find someone that takes my insurance.

Go to the insurance company web site.

Several years ago a law was passed requiring insurance companies to keep their provider lists accurate and up-to-date.

There's a regulatory window for freshness, and every insurance company web site is required by law to show you when the data was last updated.

Reply on news.ycombinator.com