shipfeedAI news, curated daily

04:04:45 CET
28 JUL04:04:45shipfeed
pull to refreshlast sync
Just in — 30 new
§ feed · storyline

OpenAI's GPT-Red beats human red-teamers on prompt injection

OpenAI announced GPT-Red, an automated red-teaming model that outperforms humans at identifying prompt injection vulnerabilities.

Jul 16 · · primary fetch1 sourceupdated Jul 16 ·

OpenAI detailed GPT-Red, an internal automated red-teaming model designed to find prompt injection vulnerabilities.

read full article on marktechpost.com
§ sources1 publication · timeline below
  1. marktechpost.comOpenAI Details GPT-Red: An Internal Automated Red-Teaming Model That Beat Human Red-Teamers 84% To 13% On Prompt Injectionprimary