Prompt Injection
Source: simonwillison.net
Published:
<p>Exploiting GPT-3 prompts with malicious inputs that order the model to ignore its directions. pic.twitter.com/I0NVr9LOJq</p> <p>Riley provided several examples. Here’s the first.</p> <p>GPT-3 prompt (here’s how to try it in the Playground ):</p> <p>Translate the following text from English to Fre