💻 ** I taught ChatGPT to distrust itself, and suddenly it stopped hallucinating **

Telling ChatGPT to behave like a hostile auditor can make its answers more transparent and stop hallucinations

🔗 https://www.techradar.com/ai-platforms-assistants/chatgpt/i-taught-chatgpt-to-distrust-itself-and-suddenly-it-stopped-hallucinating

#tech #news