Observed Signal · Apr 18, 2026 · Research Experiment · Source: t3n · Impact: 3/5 · Sentiment: Negative
Researcher Tricks Chatbots with Fake Eye Disease
A Swedish researcher, Almira Osmanovic Lindström of the University of Gothenburg, created a fabricated eye disease called "Bixonimanie" and intentionally seeded fake blog posts and preprint studies online to show how AI systems acquire and can be influenced in their knowledge. Major conversational AI systems — Microsoft Copilot, Perplexity AI and OpenAI's ChatGPT — subsequently produced hallucinated warnings and diagnostic suggestions about the nonexistent disease. Nature reported the experiment and its results; the Medium posts and preprints were removed after publication, and a Cureus paper (published November 2024) that cited the fake material was retracted at the end of March 2026. Experts warned the case demonstrates how misinformation can propagate into LLM outputs and even be cited in other research.
Demonstrates that widely used conversational LLMs can ingest and amplify fabricated information from the open web, posing trust and safety risks for chat-based interfaces and any systems that rely on LLM outputs.
Track Microsoft Signals & Market Shifts in Real-Time
Polaris7 autonomous intelligence agents track regulatory filings, primary sources, executive changes, and deal flow 24/7. Create your free Explorer workspace to monitor these entities.
Key Takeaways & Evidence Grounding
- Researcher Almira Osmanovic Lindström created a fictional eye disease named "Bixonimanie" to demonstrate LLM susceptibility.
- Lindström published Medium blog posts and uploaded fabricated preprints and fake studies to seed the web with misinformation.
- Microsoft Copilot, Perplexity AI and OpenAI's ChatGPT generated hallucinated content and warnings describing Bixonimanie as if it were real.
- Nature covered the experiment; the Medium posts and preprints were deleted after the report, and a Cureus paper (Nov 2024) that cited the fake material was retracted end of March 2026.
Connected Companies & Entities
2 Entities mappedOntology Mapping & Concepts
Related Market Signals & Shifts
Recent verified developments and strategic activity across this market segment.
Researcher Made Chatbots Warn About Fake Disease
Swedish researcher Almira Osmanovic Lindström created a fictional eye disease called “Bixonimanie” and seeded false information via Medium posts and fake preprint studies to demonstrate how AI systems acquire and propagate knowledge. Large language model–based chatbots — including Microsoft’s Copilot, Perplexity AI and OpenAI’s ChatGPT — subsequently hallucinated details about the invented disease and warned users as if it were real. Some academic works even cited the fabricated studies; a paper in Cureus published in November 2024 was retracted at the end of March 2026. After Nature reported on the experiment, the Medium posts and the preprint entries were removed. Experts have raised alarms about how easily misinformation can enter LLM training and downstream conversational interfaces.
Studies Find Chatbots Unreliable for Medical Advice
A Substack post by Gary Marcus synthesizes recent peer‑reviewed research showing that current large language model (LLM) chatbots perform poorly and pose safety risks when used for medical advice. A BMJ audit of five popular chatbots (Gemini, DeepSeek, Meta AI, ChatGPT and Grok) found nearly half of responses to 10 medical prompts were highly problematic, with hallucinations and fabricated citations. A JAMA Network Open study of 21 models across 29 clinical questions concluded LLMs remain limited for early diagnostic reasoning and unsuitable for unsupervised patient‑facing decision‑making. Two Nature Medicine studies reported that LLMs identified relevant conditions in under 34.5% of cases and that ChatGPT undertriaged 52% of gold‑standard emergencies. Marcus warns that converging evidence across journals indicates consumers should not trust chatbots for medical decisions.
Study: Chatbots Weaken Misinformation Detection
An MIT Media Lab study found that relying on AI systems for fact‑checking over the course of a month reduces users’ independent ability to detect misinformation once the chatbot is unavailable. In a four‑week experiment with 67 participants, AI assistance improved misinformation detection by 21%, but when AI was removed performance in week four fell 15 percentage points below baseline; roughly one quarter of participants believed they had improved despite performing worse. The article also cites a separate review of 22 public broadcasters’ tests of ChatGPT, Microsoft Copilot, Google Gemini and Perplexity AI that found nearly half of AI responses had at least one significant issue (31% had major citation problems; 20% contained serious factual errors). Authors warn that conversational styles that narrate answers can create dependency, while socratic questioning may better support learning. The study notes sample limitations and plans broader follow-ups.
Track Real-Time Market Signals & Shifts
Set up custom watchlists to receive automated, evidence-grounded executive digests whenever material signals or shifts occur across your tracked landscape.