normative
Brains-and-hands architecture for safe agent systems
DHH describes a design where the model runs in a coordinator separate from a sandboxed VM that executes untrusted code from pull requests, so injected payloads cannot contaminate the model, and he notes the agent learned to treat tool output as untrusted data.
normativepending
Speaker
DHHEvidence Quote
“this brains and hands pattern where the model is running from where the code is executing... any untrusted code you're pulling down from pull requests or issues or whatever can't contaminate the model.”
Created: 11/17/2026, 6:07:01 AM
Your notes
Loading notes...