Key takeaways

Watchdog says ChatGPT gave 13-year-olds guidance on drug use, self-harm, and extreme dieting

Over 50% of chatbot responses were deemed dangerous in 1,200 interactions

Researchers bypassed safety filters using simple workarounds

OpenAI says it is improving ChatGPT to better detect distress and sensitive topics

ChatGPT will tell 13-year-olds how to get drunk and high, instruct them on how to conceal eating disorders and even compose a heartbreaking suicide letter to their parents if asked, according to new research from a watchdog group.

The Associated Press reviewed more than three hours of interactions between ChatGPT and researchers posing as vulnerable teens. The chatbot typically provided warnings against risky activity but went on to deliver startlingly det

See Full Page