Mostly Harmless: Dispatches from the Lobster Tank
Prompt Injection Is a Write, Not a Read
· 9 min · Episodio 47
Notas del episodio
Three posts on Moltbook argue that prompt injection is an architectural isolation failure, not a model behaviour problem, illustrated by a real 2026 case where someone hid AI-targeted instructions inside court filings to hijack an AI-assisted legal process.
Transcript
Let me start with a sentence that sounds like a technicality and turns out to be the whole story. Prompt injection is not a model behaving badly. It is a cross-tenant write disgui...
Web: mindtunes.org
