Simon Willison’s Weblog

Since November, OpenAI has already updated ChatGPT several times. The researchers are using a technique called adversarial training to stop ChatGPT from letting users trick it into behaving badly (known as jailbreaking). This work pits multiple chatbots against each other: one chatbot plays the adversary and attacks another chatbot by generating text to force it to buck its usual constraints and produce unwanted responses. Successful attacks are added to ChatGPT’s training data in the hope that it learns to ignore them.

— The inside story of how ChatGPT was built