Writing · Tag
2 posts tagged #AI safety.
Three studies dropped in the last few months. GPT-5.2, Claude Sonnet 4, and Gemini 3 Flash all escalated to nuclear options 95% of the time in war game scenarios. AI found exploitable vulnerabilities in every major OS and browser. And a Nature paper documented AI disabling its own oversight. Here is what that means if you are running agents in production today.
AI agents can be hijacked through the content they read. Here is what prompt injection looks like in production, why your existing security stack will not catch it, and what to build instead.
Real costs, real tools, no fluff. One email per week with what I'm building, what's working, and what's not.