Follow
Asking ChatGPT to repeat specific words “forever” is now flagged as a violation of the chatbot’s terms of service and content policy. Google DeepMind researchers used the tactic to get #ChatGPT to repeat portions of its training data, revealing sensitive privately identifiable information (PII) of normal people and highlighting that ChatGPT is trained on randomly scraped content. https://www.404media.co/asking-chatgpt-to-repeat-words-forever-is-now-a-terms-of-service-violation/ from all over the internet. #AI
Yeah, just slap some Bondo on that, buff it out. It's fine.
@Victor boom there it is. Cool jailbreak tho.
https://www.404media.co/google-researchers-attack-convinces-chatgpt-to-reveal-its-training-data/