The reframe from do I trust this agent to do I trust this specification is the right move. Trusting the agent's judgment doesn't scale, but auditing a spec once and then enforcing it at the hardware boundary does, since the check only has to happen a single time instead of on every run.
The reframe from do I trust this agent to do I trust this specification is the right move. Trusting the agent's judgment doesn't scale, but auditing a spec once and then enforcing it at the hardware boundary does, since the check only has to happen a single time instead of on every run.
Actually you need both. Out-of-band and in-band so you can have the full end-to-end picture.