The security model we've relied on for decades assumes the thing inside the boundary…
This is a AI post classified by Jev as AI agents (a free resource), kept by the AI Radar because it carries real work, not commentary.
The security model we've relied on for decades assumes the thing inside the boundary does what it's told. Justin Kuiper of @futuretechny has operated where that failing has real consequences. He and Per Krogslund on governing agents when you can't get it wrong: https://bit.ly/46DTzdJ
Posted by Docker (556.1k followers) 54 min ago · 4 likes · 1.2k views · view the original post on X. Kept by the AI Radar as AI agents.
More AI work like this
- Univer is now Top 3 on GitHub Trending.🚀 — @LeonUniver
- Grok Build v1.0.41 is out with a few practical updates. Standouts include added a new… — @blankspeaker
- MOST WORK STARTS AS A PROMISE IN AN EMAIL — @DataChaz
- Why did we build our own Android and iPhone apps for Nautilo? Why didn't we just do what… — @Dan_Jeffries1
- Cool paper showing how effective tuning a system prompt for an agent can be. — @dair_ai
- Grok Bot just released for Tesla and I'm blown away — @AlexFinn
- JUST IN: DigitalOcean launches ‘Managed Agents’ in public preview, bringing AI agent… — @WhaleInsider
- A NEW CLOUD ERA FOR AI AGENTS IS HERE — @DataChaz
Every post is read and classified by Jev (TypeSafe): what it is, which market it belongs to, and whether the link is a real tool. 42.2k posts from 5k X accounts over the last 14 days, 1.8k tools, 19 markets. Collected every 5 minutes, fully re-ranked every hour — last update 2026-09-22 16:47 UTC. Full method.