A team of researchers primarily from Google’s DeepMind systematically convinced ChatGPT to reveal snippets of the data it was trained on using a new type of attack prompt which asked a production model of the chatbot to repeat specific words forever. Using this tactic, the researchers showed that there are large amounts of privately identifiable information (PII) in OpenAI’s large language m ... ⌘ Read more
A team of researchers primarily from Google’s DeepMind systematically convinced ChatGPT to reveal snippets of the data it was trained on using a new type of attack prompt which asked a production model of the chatbot to repeat specific words forever. Using this tactic, the researchers showed that there are large amounts of privately identifiable information (PII) in OpenAI’s large language m ... ⌘ Read more