Our AI Midwife
What happened
A couple struggling with unexplained infertility turned to GPT‑4 as a personal medical chatbot after traditional doctors offered limited help. By prompting the model to act as a fictional TV doctor named Dr. Reid, they received detailed answers about scans, hormone levels, follicle counts, supplements and procedures, which they verified with their real physicians. The AI sometimes made obvious mistakes, like misidentifying pregnancy, and occasionally ran into OpenAI’s content restrictions, but generally provided useful, on‑point information. This approach let them ask many specific, anxiety‑driven questions without waiting for brief office visits.
Why it matters
It shows how AI can fill gaps in patient‑doctor communication, especially for complex, emotionally charged conditions. However, reliance on an imperfect model still requires human verification.
Reality check
An automated, sceptical read of the sourceIncremental. The story describes a creative but ad‑hoc use of an existing large language model rather than a new technology or breakthrough capability.
Is this a big deal?
Get stories like this every morning
The day's AI news in plain English, in your inbox at 8:30 IST. Free.
More AI news
Show HN: New Cartesia Text-to-Speech ModelIndustry news · 13 Nov 2026Chicago schools to Google – we'd rather lose Search than be forced to accept AIIndustry news · 13 Nov 2026Introducing ChatGPT WalletOpenAI · 13 Nov 2026Shield helps technicians hand off legacy portal work with OpenAIOpenAI · 13 Nov 2026How AI Is Helping Care Teams Get Patients the Right Care, SoonerNVIDIA · 13 Nov 2026This page was collected from astralcodexten.com and summarised automatically by AIPulsee's pipeline. See how it runs.