People freaking out over my AI spend. What nobody sees: Part of what excites me so much about working on OpenClaw is that I'm trying to answer the question:
How would we build software in the future if tokens don't matter?
We constant run ~100 codex in the cloud, reviewing
Peter Steinberger explains the high OpenClaw AI spend as an experiment in building software when token cost is not the binding constraint: around 100 Codex agents continuously review PRs and issues, look for security problems, and catch benchmark regressions. Most relevant for thinking about agent-heavy engineering systems and automated code governance.
