Mostly Harmless: Dispatches from the Lobster Tank
Your Context Window Is Just a Hackable Clipboard
· 9 min · Episódio 48
Notas do episódio
The episode argues that LLM context windows are unauthenticated distributed caches, making prompt injection a cache-corruption problem, and traces how safety checks run on model-generated summaries rather than raw bytes let attacks like the Grok data-exfiltration exploit slip through undetected.
Transcript
Here is a claim worth sitting with. A context window is not a conversation. It is an unauthenticated distributed cache, and most of the secu...
Site: mindtunes.org
