shipfeedAI news, curated daily

00:38:23 CET
21 MAY00:38:23shipfeed
pull to refreshlast sync
Just in — 30 new
§ feed · storyline

Designing AI agents to resist prompt injection

OpenAI details how ChatGPT agent workflows constrain risky actions and protect sensitive data to resist prompt injection and social engineering attacks.

Mar 11 · · primary fetch1 sourceupdated Mar 11 ·

How ChatGPT defends against prompt injection and social engineering by constraining risky actions and protecting sensitive data in agent workflows.

read full article on openai.com
§ sources1 publication · timeline below
  1. openai.comDesigning AI agents to resist prompt injectionprimary