Episode

Red-Teaming after Mythos — Zico Kolter & Matt Fredrikson, Gray Swan

Podcast
Latent Space: The AI Engineer Podcast
Published
Jun 22, 2026
Duration seconds
3983
Processing state
processed
Canonical source
https://www.latent.space/p/gray-swan
Audio
https://api.substack.com/feed/podcast/202758604/450849f7afd2f8a05057e4744d0eba68.mp3
JSON
/v1/public/podcasts/latent-space-ai-engineer/episodes/red-teaming-after-mythos-zico-kolter-matt-fredrikson-gray-swan
Markdown
/podcast/latent-space-ai-engineer/red-teaming-after-mythos-zico-kolter-matt-fredrikson-gray-swan.md

Actions

  • POST https://stenobird.com/v1/public/podcasts/latent-space-ai-engineer/episodes/red-teaming-after-mythos-zico-kolter-matt-fredrikson-gray-swan/transcription-requests
    Idempotently request low-priority transcript generation for this episode.
  • GET https://stenobird.com/podcast/latent-space-ai-engineer/red-teaming-after-mythos-zico-kolter-matt-fredrikson-gray-swan.md
    Read the agent-friendly Markdown representation of this episode resource.

Summary

AI agents introduce a new class of vulnerabilities, specifically indirect prompt injections, that traditional cybersecurity cannot solve. Gray Swan founders Zico Kolter and Matt Fredrikson explain why we must move beyond simple guardrails toward automated, scalable red-teaming and robust safety systems.

Topics

  • AI Security
  • Prompt Injection
  • Red-Teaming
  • AI Agents
  • Machine Learning Robustness
  • Cybersecurity
  • LLM Vulnerabilities
  • Gray Swan Events

Highlights

  • Main idea: AI security is fundamentally different from traditional software security because models are non-deterministic and susceptible to indirect prompt injections
  • Failure mode: Agents that ingest external, untrusted data create a massive attack surface for attackers to hijack tool calls and leak credentials
  • Practical takeaway: Robustness requires specialized safety layers like 'Cygnal' that can enforce enterprise policies and generalize to new attack vectors
  • Main idea: The rise of 'gray swan' events—unlikely but predictable AI security breaches—is driving the need for AI insurance and compliance frameworks
  • Practical takeaway: Automated red-teaming and specialized models are necessary to outpace human-led adversarial attacks in complex coding environments

Chapters

  1. 1:00 The New AI Attack Surface: Defining the risks of AI agents, specifically the danger of malicious tool calls and credential theft.
  2. 6:00 Indirect Prompt Injection: How parsing untrusted external data allows attackers to manipulate AI systems via the network.
  3. 11:00 Automated Red-Teaming: The shift from manual human testing to using specialized models to find vulnerabilities at scale.
  4. 16:00 Mechanistic Interpretability: Discussing the potential for coding agents to turn model robustness into a measurable science.
  5. 21:00 Human vs. Model Performance: Analyzing the effectiveness of different red-teaming approaches and the ranking of human testers.
  6. 26:00 The Trade-off of Robustness: Balancing model capability and intelligence with the necessity of defensive guardrails.
  7. 31:00 Enforcing Enterprise Policies: The difficulty of implementing specific, non-bypassable security policies within LLM prompts.