We asked a 7-year-old and a CISO the same AI security question 🧸
This is a dev post classified by AGK Intelligence as Security (a free resource), kept by the Dev Radar because it carries real work, not commentary.
We asked a 7-year-old and a CISO the same AI security question 🧸 Wiz researcher Aviel Erdis explains AI agent security five times, to 5 very different people in 5 different levels of understanding. It starts with a kid and ends with a seasoned security expert who has heard every pitch in the book. The kid stole the show (sorry, CISO). 🐣 Watch all 5 levels ⤵ https://youtu.be/xDBbDPALXPs
Posted by Wiz (26.4k followers) 4 h ago · 4 likes · 552 views · view the original post on X. Kept by the Dev Radar as Security.
More dev work like this
- If an agent works all night under an employee’s login, whose actions appear in the… — @Cloudflare
- 🚨If you're in cybersecurity, DON'T miss this 🙏 — @chrisdior777
- How I'd start bug bounty hunting in 2026. — @CristiVlad25
- New guidance on open-weight AI models is now available. Learn about the opportunities,… — @ASDGovAu
- Your AI security has a blind spot: the endpoint. — @zscaler
- 🚨 A PackageKit race condition can let a local unprivileged user gain root access on… — @DarkWebInformer
- 🚨 A Samba printing flaw can turn a malicious print job name into remote code execution;… — @DarkWebInformer
- Our security researchers built an autonomous cyber vulnerability discovery,… — @OpenAI
Every post is read and classified by AGK Intelligence: what it is, which market it belongs to, and whether the link is a real tool. 31.7k posts from 5k X accounts over the last 21 days, 9.4k tools, 12 markets. New posts are collected several times an hour and the full ranking is recomputed every hour — last update 2026-11-05 14:03 UTC. Full method.