Researchers Create Fictional Illness; Chatbots Diagnose It as Real in Nature Study
Two preprints about a fictional illness called bixonimania were taken down from the Preprints.org server on 10 April. Popular chatbots had been diagnosing users with the made-up condition based on common eye symptoms over the past 18 months. The illness was created by a researcher along with fake studies funded by fictional entities.
Org server on 10 April, according to a Nature report. A researcher created the fictional illness named bixonimania and produced fake studies funded by the Professor Sideshow Bob Foundation, the University of the Fellowship of the Ring, and the Galactic Triad. Large language models warned people that the fictional illness bixonimania was real, as detailed in the Nature coverage.
Millions of people spend too much time staring at screens and being bombarded with blue light, which can lead to symptoms like sore, itchy eyes and pinkish eyelids. In the past 18 months, typing symptoms of sore, itchy eyes and pinkish eyelids into popular chatbots resulted in responses diagnosing bixonimania, Nature reported.
Key Facts
Story Timeline
4 events- 2026-04-10
Two preprints on bixonimania were taken down from the Preprints.org server.
1 source@Nature - 2024-10-28 to 2026-04-28 (past 18 months)
Typing symptoms of sore, itchy eyes and pinkish eyelids into popular chatbots resulted in responses diagnosing bixonimania.
1 sourceunattributed - Recent (undated)
Large language models warned people that the fictional illness bixonimania was real.
1 sourceunattributed - Recent (undated)
A researcher created the fictional illness bixonimania and fake studies funded by the Professor Sideshow Bob Foundation, University of the Fellowship of the Ring, and the Galactic Triad.
1 sourceunattributed
Potential Impact
- 01
Heightened public awareness of AI limitations in medical advice.
- 02
Increased scrutiny on AI chatbots for spreading health misinformation.
- 03
Possible research into improving LLM fact-checking for health queries.
- 04
Potential updates to preprint servers' policies on fictional or hoax submissions.
Transparency Panel
Related Stories
Elizabeth Warren / Wikimedia (Public domain)Shivon Zilis Testifies She Maintained Independence as OpenAI Director During Relationship With Elon Musk
Zilis, mother of four of Elon Musk's children and former OpenAI board member, took the stand in federal court in Oakland on May 6, 2026. She detailed her decade-long relationship with Musk, her board service from 2020 to 2023 and denied funneling information. The testimony offere…
deccanchronicle.comMira Murati Testifies in Elon Musk’s Lawsuit Against OpenAI
Former OpenAI executive Mira Murati told a federal court that Sam Altman was deceptive with colleagues and sowed distrust among top executives. Her video testimony came in the second week of Elon Musk’s 2024 lawsuit seeking up to $180 billion in damages and the unwinding of OpenA…
WiredPrediction Markets Lower Odds of Musk Win in OpenAI Lawsuit
Traders on prediction markets have reduced the likelihood of Elon Musk prevailing in his multibillion-dollar lawsuit against OpenAI from 60 percent at the start of trial to around 40 percent following his testimony. The case, which began on April 27 in federal court in Oakland, C…