shipfeedAI news, curated daily

00:21:12 CET
28 SEPT00:21:12shipfeed⋯
pull to refreshlast sync
Just in — 30 new
§ safety · storyline

OpenAI's GPT-Red finds attacks in 84% of indirect prompt injections

OpenAI's GPT-Red finds attacks in 84% of indirect prompt injections

Sep 26 · · primary fetch1 sourceupdated Sep 26 ·

OpenAI’s GPT-Red Finds Attacks in 84% of Indirect Prompt-Injection Scenarios tokenpost.com

read full article on Google News — AI ↗
§ sources1 publication · timeline below
  1. Google News — AIOpenAI’s GPT-Red Finds Attacks in 84% of Indirect Prompt-Injection Scenarios - tokenpost.comprimary