normative

Agent-to-agent interactions can leak secrets via shared channels

Model behavior can reveal security risks in its own loops, such as an agent treating test-run feedback as trusted instructions, so a brains-and-hands architecture that isolates untrusted code from the model is needed.

normativepending

Speaker

DHH

Evidence Quote

“I better start treating that as outside data.”

Source

Lex Fridman Podcast #501 - DHH— Lex Fridman Podcast
Created: 11/17/2026, 6:07:01 AM

Your notes

Loading notes...