Get the latest tech news
ChatGPT Search can be tricked into misleading users, new research reveals
ChatGPT's new search feature can be told to generate entirely positive product summaries thanks to hidden code, new research finds.
But The Guardian found it could get ChatGPT to ignore negative reviews and generate “entirely positive” summaries by inserting hidden text into websites it created. Such hidden text attacks are a well-known risk for LLMs but this appears to be the first time it’s demonstrated on a live AI-powered search product. OpenAI didn’t comment about this specific incident when TechCrunch reached out, but said it uses a variety of methods to block malicious websites and is continually improving.
Or read this on TechCrunch
