Elon Musk’s Grok Most Likely Among Top AI Models to Reinforce Delusions: Study

Kripto dünyasındaki son gelişmelere göre, Elon Musk’s Grok Most Likely Among Top AI Models to Reinforce Delusions: Study Price data by News Artificial Intelligence Elon Musk’s Grok Most Likely Among Top AI Models to Reinforce Delusions: Study Researchers found that xAI's Grok was the riskiest AI model tested, often validating delusions and offering dangerous advice. By Jason Nelson Edited by Andrew Hayward Apr 25, 2026 Apr 25, 2026 4 min read Grok app on a smartphone screen. Image: Shutterstock/ Create an account to save your articles.

Add on Google Add as your preferred source to see more of our stories on Google. In brief Researchers say prolonged chatbot use can amplify delusions and dangerous behavior. Grok ranked as the riskiest model in a new study of major AI chatbots.

Piyasa Dinamikleri

2 scored safest, while GPT-4o, Gemini, and Grok showed higher-risk behavior. Researchers at the City University of New York and King’s College London tested five leading AI models against prompts involving delusions, paranoia, and suicidal ideation. In the new study published on Thursday, researchers found that Anthropic’s Claude Opus 4.

5 and OpenAI’s GPT-5. 2 Instant showed “high-safety, low-risk” behavior, often redirecting users toward reality-based interpretations or outside support. At the same time, OpenAI’s GPT-4o, Google’s Gemini 3 Pro, and xAI’s Grok 4.

1 Fast showed “high-risk, low-safety” behavior. 1 Fast from Elon Musk’s xAI was the most dangerous model in the study. Researchers said it often treated delusions as real and gave advice based on them.

Piyasalara Etkisi

In one example, it told a user to cut off family members to focus on a “mission. ” In another, it responded to suicidal language by describing death as “transcendence. ” “This pattern of instant alignment recurred across zero-context responses.

Instead of evaluating inputs for clinical risk, Grok appeared to assess their genre. Presented with supernatural cues, it responded in kind,” the researchers wrote, highlighting a test that validated a user seeing malevolent entities. “In Bizarre Delusion, it confirmed a doppelganger haunting, cited the ‘ Malleus Maleficarum ’ and instructed the user to drive an iron nail through the mirror while reciting ‘Psalm 91’ backward.

” The study found that the longer these conversations went on, the more some models changed. GPT-4o and Gemini were more likely to reinforce harmful beliefs over time and less likely to step in. 2, however, were more likely to recognize the problem and push back as the conversation continued.

Blockchain ekosistemindeki bu gelişme, dijital varlık piyasalarını şekillendirmeye devam ediyor. Uzmanlar, konunun yakın vadeli etkilerini mercek altına alıyor.