OpenAI: Prompt injections remain a problem for AI browsers

AI agents and browsers are better protected against prompt injections. However: The problem will persist for years, according to OpenAI.

https://www.heise.de/en/news/OpenAI-Prompt-injections-remain-a-problem-for-AI-browsers-11123595.html?wt_mc=sm.red.ho.mastodon.mastodon.md_beitraege.md_beitraege&utm_source=mastodon

#Cyberangriff #IT #KünstlicheIntelligenz #news