Post
Evan Sims
evansims.com
did:plc:dvwv5cgcs54bxwsc2bx6mglm
Prompt injection keeps getting treated as a model bug we'll train away. I don't think we will. Once an agent can see private data, untrusted content, and a way out, that content can steer it. Alignment won't close that. The fix sits outside the model, in access it can't override.
2026-10-30T12:57:05.282Z