Simon Willison’s Weblog

Subscribe

Tuesday, 21st October 2025

Prompt injection might be unsolvable in today’s LLMs. LLMs process token sequences, but no mechanism exists to mark token privileges. Every solution proposed introduces new injection vectors: Delimiter? Attackers include delimiters. Instruction hierarchy? Attackers claim priority. Separate models? Double the attack surface. Security requires boundaries, but LLMs dissolve boundaries. [...]

Poisoned states generate poisoned outputs, which poison future states. Try to summarize the conversation history? The summary includes the injection. Clear the cache to remove the poison? Lose all context. Keep the cache for continuity? Keep the contamination. Stateful systems can’t forget attacks, and so memory becomes a liability. Adversaries can craft inputs that corrupt future outputs.

Bruce Schneier and Barath Raghavan, Agentic AI’s OODA Loop Problem

# 2:28 am / bruce-schneier, security, ai, prompt-injection, llms, ai-agents

Since getting a modem at the start of the month, and hooking up to the Internet, I’ve spent about an hour every evening actually online (which I guess is costing me about £1 a night), and much of the days and early evenings fiddling about with things. It’s so complicated. All the hype never mentioned that. I guess journalists just have it all set up for them so they don’t have to worry too much about that side of things. It’s been a nightmare, but an enjoyable one, and in the end, satisfying.

Phil Gyford, Diary entry, Friday February 17th 1995 1.50 am

# 2:40 am / computer-history, phil-gyford

2025 » October

MTWTFSS
  12345
6789101112
13141516171819
20212223242526
2728293031