Language models like ChatGPT and Sydney, which powers Bing Chat, are vulnerable to malicious prompt engineering. Mitigating them will be hard.| TechCrunch
We go hands-on with Microsoft's new ChatGPT-like features in its Bing search engine.| TechCrunch
Riley Goodside, yesterday: Exploiting GPT-3 prompts with malicious inputs that order the model to ignore its previous directions. pic.twitter.com/I0NVr9LOJq- Riley Goodside (@goodside) September 12, 2022 Riley provided several examples. Here’s …| Simon Willison’s Weblog