Researchers found a simple way to make ChatGPT, Bard, and other chatbots misbehave, proving that AI is hard to tame. Thanks for listening to WIRED. Talk to you next time for more stories from WIRED.com and read this story here.

<p>Researchers found a simple way to make ChatGPT, Bard, and other chatbots misbehave, proving that AI is hard to tame. Thanks for listening to WIRED. Talk to you next time for more stories from WIRED.com and read this story <a href="https://www.wired.com/story/ai-watermarking-misinformation/">here</a>.</p>

The latest in-depth coverage covering the intersection of technology and culture. WIRED’s award-winning journalism will help you make sense of a world in constant transformation. Join us as we explore the ways technology is changing our lives.

Advertisement