Series

Posts that belong together, in reading order.

  • Adversarial Mindset

    3 parts on this site

    The case for the adversarial mindset, what it costs, and how it works in practice.

  • Local Red-Team AI

    2 parts on this site

    Can open-weight models you run on your own hardware do real red-team work, and can you trust the benchmark that says so?

  • On Red Teams

    1 part on this site

    What a red team actually is, revisited seven years after the first attempt.

← All posts