tobiassommer.bsky.social
@tobiassommer.bsky.social
Reposted by tobiassommer.bsky.social
Final call! Join us @unibielefeld as a post-doc or PhD student (3yrs). Application deadline 1.12. Join any of our ongoing projects e.g., work on living analyses with big data (individual diff., neg. affect) or early adversity or ENIGMA fear conditioning
tinyurl.com/36n5wu3s
tinyurl.com/36n5wu3s
Wissenschaftliche*r Mitarbeiter*in (m/w/d) (Postdoc oder Doktorand*in)
tinyurl.com
November 29, 2023 at 4:09 PM
Final call! Join us @unibielefeld as a post-doc or PhD student (3yrs). Application deadline 1.12. Join any of our ongoing projects e.g., work on living analyses with big data (individual diff., neg. affect) or early adversity or ENIGMA fear conditioning
tinyurl.com/36n5wu3s
tinyurl.com/36n5wu3s
Reposted by tobiassommer.bsky.social
"A team of researchers primarily from Google’s DeepMind systematically convinced ChatGPT to reveal snippets of the data it was trained on...[this ]showed that there are large amounts of privately identifiable information (PII) in OpenAI’s large language models." www.404media.co/google-resea...
Google Researchers’ Attack Prompts ChatGPT to Reveal Its Training Data
ChatGPT is full of sensitive private information and spits out verbatim text from CNN, Goodreads, WordPress blogs, fandom wikis, Terms of Service agreements, Stack Overflow source code, Wikipedia page...
www.404media.co
November 29, 2023 at 5:26 PM
"A team of researchers primarily from Google’s DeepMind systematically convinced ChatGPT to reveal snippets of the data it was trained on...[this ]showed that there are large amounts of privately identifiable information (PII) in OpenAI’s large language models." www.404media.co/google-resea...