PLAY PODCASTS
Forever Fragile: OpenAI on AI Agent Prompt Risks

Forever Fragile: OpenAI on AI Agent Prompt Risks

Good AI · Good AI

January 3, 202614m 52s

Audio is streamed directly from the publisher (rss.art19.com) as published in their RSS feed. Play Podcasts does not host this file. Rights-holders can request removal through the copyright & takedown page.

Show Notes

OpenAI declares AI agents forever fragile against prompt injection regardless of scale or training. Adversaries craft contextually invisible payloads derailing objectives maliciously. Industry pivot needed to formal methods transcending probabilistic LLM foundations.


See Privacy Policy at https://art19.com/privacy and California Privacy Notice at https://art19.com/privacy#do-not-sell-my-info.