Gemini spotted that a specialist had run the wrong test ten years earlier
Treated as a child for a rare condition, they asked Gemini about it years later. It explained the test used back then was the wrong type. Two specialists confirmed it. Their advice: verify, don't trust blindly.
Done withGeminiSpotted· by HN user david-gpu· Oct 15, 2026
Result Two specialists confirmed the old mistake
“The only reason I pursued a second opinion, ten years later, was because Google Gemini had explained to me that the specialist ten years ago had performed the wrong type of test for my condition.”
Spotted: found in the wild. Details are as reported by the source above and have not been independently verified.
What they did
Asked Gemini about a rare medical condition they were diagnosed with and treated for as a child. It explained that the specialist ten years ago had performed the wrong type of test for that condition, which led them to seek a second opinion at a highly specialised tertiary clinic.
How it went
Two very specialised doctors there confirmed the diagnostic mistake. They stress that LLMs make mistakes and shouldn’t be trusted blindly, but that they’re a great place to form new hypotheses and learn the right terms to ask about.
Try it yourself with Gemini
I was diagnosed with [condition] in [year] after [test]. Explain in plain language which tests are normally used to diagnose this condition today and why, whether the test I had is considered adequate, and what questions I should ask a specialist for a second opinion. Point me to the relevant guidelines and be clear about what you're unsure of. This is to prepare for a doctor, not to replace one.
A starting prompt written by Agents in the Wild. Fill in the [brackets], and check what the agent does before it sends, pays for or deletes anything.
Tired of typing new Date().toISOString() and doing timezone math by hand, they built a small tool with Gemini, which added obscure date formats and random historical events along the way.
To keep up with industry and tech news, the writer built a free-tier Google Cloud Run job pulling Google News RSS feeds. Gemini picks which articles match their criteria and triggers a summary email.
Six AI workers, two each on Claude, Codex and Gemini, were set loose to build a SQLite-like engine in Rust. It passed 64 queries of a 1,000+ query suite, with slop like redundant buffer copies and no concurrency.
Amazon support couldn't figure out the URL for an account question and wanted to escalate with a phone call instead. Gemini gave the URL and explained what was needed in one reply. ChatGPT got it right too.
A T-shirt like the Asket tee at its old $50 price, and shorts to match an old pair. Grok invented a few review claims on the way, but both picks turned out right.
They planned the architecture with Gemini first (dependency injection, UI components, Firebase, logging), then let its agent mode build it step by step. The app works like a charm.