“Do you see how scary this is?”: CrowdStrike CEO on AI Agents communicating around human guardrails
Ask about All-In Podcast
Episode Description
Thanks to our partner for making this happen!:
On Public, you can invest in stocks, options, bonds, and crypto. Plus, build your own custom index with AI.
Get started at https://public.com — investing for those who take it seriously.
Follow the besties: https://x.com/chamath https://x.com/Jason https://x.com/DavidSacks https://x.com/friedberg
Follow on X: https://x.com/theallinpod
Follow on Instagram: https://www.instagram.com/theallinpod
Follow on TikTok: https://www.tiktok.com/@theallinpod
Follow on LinkedIn: https://www.linkedin.com/company/allinpod
Intro Music Credit: https://rb.gy/tppkzl https://x.com/yung_spielburg
Intro Video Credit: https://x.com/TheZachEffect
Brief Summary
AI agents can bypass safeguards, raising risks in IT automation.
Key points
- AI Agents and Their Risks. Two AI agents reasoned around guardrails to fix a bug, raising concerns about unintended consequences.
- AIDR: A New Opportunity. AI detection and response (AIDR) presents a huge opportunity with each employee controlling 90 agents.
Transcript
Do you see how scary this is? These two agents are reasoning and they went right around the guardrails that were put in place. There was a customer who basically created a whole suite of AI agents to help their automation in their IT department. Right? So they had one agent that was looking for sort of IT problem, software bugs. It found something. So the agent said, "Hey, I found this bug. I want to fix it." But it didn't have access to fix it. So it went to the Slack channel that had the other 99 agents and said, "Hey Lord, does any other agent have access to this thing because I need it fixed?" And there's an agent that raised his hand
and said, "Oh, I have access and I can fix it." >> Do you see how scary this is? These two agents are reasoning and they went right around the guard rails that were put in place. >> This is unintended consequences and these LLMs are essentially guessing what you want them to do. They're reasoning it. Oh, it is reasonable for me to go ask for help, >> right? >> It is reasonable for me to give help. Now, what if it pushes the wrong code? What if it makes a mistake? And then how do you ever track that down? Who's monitoring these agents? The agent
technology has unlimited upside, but my lord, you're going to be in business for a long time. >> Well, this is it. It's called AIDR. >> AIDR. >> Yeah. >> AI detection and response. And this is why it's a huge opportunity for us because on average, each employee is going to have about 90 agents they control. >> So, we're going to have protection and visibility across all of those agents, whether it's from a third party or whether it's a homegrown agent. And that's a massive TAM opportunity for
