An AI researcher has coined the term "mad LLM disease" to describe a phenomenon where large language models degrade when they are trained on their own generated output. This concept is compared to mad cow disease, which results from cows consuming feed made from other cows. The researcher suggests this self-ingestion of output leads to a rapid decline in the model's performance and coherence. AI
Summary written by gemini-2.5-flash-lite from 1 sources. How we write summaries →
IMPACT Warns of potential degradation in AI model quality due to self-referential training data.
RANK_REASON The cluster discusses a conceptual risk in AI development, drawing an analogy to a biological phenomenon, rather than reporting on a specific event or release.