SN 1093: Tokens in the Stream - Why LLMs are inherently insecure and prompt injection will persist
MentionsAnthropic
Runs 2:48:10. Streams from pdst.fm only when you press play.
Turns out, every chatbot conversation runs on a messy hack at the heart of language models, making prompt injection an unsolved—and possibly unsolvable—security threat. Steve and Leo unravel the research that explains why "roles" in AI aren't what you think they are. Understanding the controversy surrounding "AI Model Distillation" Anthropic moves to make their most powerful Mythos 5 model more widely available. Bitwarden's "Secrets Manager" offering prevents agentic and prompt injection abuse.
Show notes from Security Now.
Explained
The technology and terms in this story. Learn more
- TechnologyLLM · Large language modelAn AI model trained on huge amounts of text to understand and generate language, such as ChatGPT or Claude.
- AttackPrompt injectionHiding instructions in content an AI reads, so it follows the attacker instead of its user.
- TechnologyAI agentAn AI model that acts on its own: it plans steps, uses tools and takes actions, not just answers.