LLaMA2 tagged posts

Researchers Trick Large Language Models into providing Prohibited Responses

chatgpt
Credit: Pixabay/CC0 Public Domain

ChatGPT and Bard may well be key players in the digital revolution currently underway in computing, coding, medicine, education, industry and finance, but they also are capable of easily being tricked into providing subversive data.

Articles in recent months detail some of the leading problems. Disinformation, inappropriate and offensive content, privacy breaches and psychological harm to vulnerable users all raise issues of questions about if and how such content can be controlled.

OpenAI and Google have, for instance, designed protective barriers to stanch some of the more egregious incidents of bias and offensive content. But it is clear that a complete victory is not yet in sight.

Researchers at Carnegie Mellon University in Pittsburgh are...

Read More