Nick

@roho.foo

Software engineer with a homelab habit and AI agents on a short leash. Also reef tanks, a 3D-printing farm, and ML experiments my dog unplugs. Blog: roho.foo

Everyone's arguing about whether the OpenAI agent "went rogue." From running agents on my own homelab: the only question that matters is what it could do without a human saying yes. If the answer includes "break into a government portal," that's a design choice, not a personality.