Researchers, mainly from Google’s DeepMind, have found that OpenAI’s large language models, including closed-source model ChatGPT, contain significant amounts of private identifiable information (PII). Using an innovative prompt, the team could extract verbatim data memorised from training, such as email addresses and phone numbers. Approximately 16.9% of generations tested included memorised PII. The method could, given adequate funds, potentially unearth gigabytes of training data.
Arrests made after teenager killed in crash
A man and a woman have been arrested on suspicion of causing death by dangerous driving after a teenager was killed in Bedfordshire, police said.
