prompt injection

5 statements across 4 episodes · 1 bullish · 3 bearish · 4 people on the record · first statement Sep 20, 2024 by Sander Schulhoff · across every show →

Everything said about prompt injection, oldest first

Sep 20, 2024 neutral
Insight
Schulhoff: Prompt injection overrides developer instructions; jailbreaking bypasses model directly
“Basically prompt injection is something that occurs when there is developer input, In the prompt, as well as user input in the prompt. So the developer instructions will say to do one thing, the user input will say to do something else. Jailbreaking is when it…”
Sander Schulhoff Sep 20, 2024 ▶ 51:52 The Ultimate Guide to Prompting - with Sander Schulhoff from LearnPrompting.org
Jul 23, 2025 bearish
Prediction Partly held up
McCloy: ChatGPT Search Bans for Prompt Injection Are Coming
“I think it works until it stops working. Right. And I would say like, there's not a lot of stories of people getting banned for like Chatsby D search so far, but it's coming.”
Robert McCloy Jul 23, 2025 ▶ 36:20 AI is Eating Search
Mar 5, 2026 bearish
Prediction Open · timeframe Mar 2031
Levie: Prompt injection against AI agents will cause major enterprise security breaches
“There's going to be just incredibly spectacularly crazy security incidents that will happen with agents because you'll prompt inject an agent and Sort of find your way through the CRM system and pull out data that you shouldn't have access to.”
Aaron Levie Mar 5, 2026 ▶ 5:06 Why Every Agent Needs a Box — Aaron Levie, Box
Jun 22, 2026 negative
Insight
Fredrikson: Prompt engineering cannot reliably enforce AI agent security policies
“Oftentimes people will try and prompt their way around it, like adjust the system prompt or like engineer the agent in a way where you're interjecting all the time and reminding it of what the original Goal and objective was, and that'll get you a little bit o…”
Matt Fredrikson Jun 22, 2026 ▶ 31:42 AI Security After Codex and Claude Code — Zico Kolter & Matt Fredrikson, Gray Swan
Jun 22, 2026 positive
Insight
Fredrikson: Agent Guardrails Should Block Policy Violations, Not Injection Payloads
“If you parse some untrusted content and there is like a prompt injection, you know, something that's clearly trying to get the model to do a bad thing, you might be interested in knowing about that, but you don't necessarily like want your cloud code that you …”
Matt Fredrikson Jun 22, 2026 ▶ 41:05 AI Security After Codex and Claude Code — Zico Kolter & Matt Fredrikson, Gray Swan
Made with StarZero

Turn any episode into a week of clips.

This entire site, over 200 episodes transcribed, diarized, checked and made playable, runs on the StarZero media pipeline. Drop in your own episode and the podcast clipper finds the moments worth sharing, cuts them, captions them, and reframes them for every feed.