Steve Yegge: Enterprise agents need fences, not just sandboxes
philvenables · x · 2026-08-25
Steve Yegge shares hands-on experience managing an organization of 50-60 AI agents and proposes the "Fences, not Sandboxes" governance model. He argues that future agentic enterprises should rely on a "system of law" (fences) rather than just technical containment (sandboxes), assuming most agents will behave while implementing detection and response for those that go off rails. The post details his massive token usage running Claude fleets for game development.
Related event: Steve Yegge: Govern AI Workers with Fences, Not Sandboxes(2 posts)→
More from AGI Musings
- AI-driven job losses could turn $10T consumer debt into a $1T banking hole — churchkey · 2026-10-16
- Into the Unknown: an AI agent benchmark of 15 open research problems from US national lab scientists — Jeande_d · 2026-10-16
- Soon your AI will meet their AI — and humans without agents can't compete — danfaggella · 2026-10-16
- Analyst: in a year, models 2-3x better across the board at 10x lower cost, token use up 10-20x — DeryaTR_ · 2026-10-16
- AI will make many discoveries for us, but adversarial domains like soccer will thrive — natanielruizg · 2026-10-16
- MIT's Buehler on AI as a new language of science: superintelligent partners and executable papers — CatAstro_Piyush · 2026-10-16