Oxide and Friends

Adversarial Machine Learning

Oxide and Friends

Nicholas Carlini joined Bryan, Adam, and the Oxide Friends to talk about his work with adversarial machine learning. He's found sequences of--seemingly random--tokens that cause LLMs to ignore their restrictions! Also: printf is Turing complete?!

In addition to Bryan Cantrill and Adam Leventhal, we were joined by special guest Nicholas Carlini.

If we got something wrong or missed something, please file a PR! Our next show will likely be on Monday at 5p Pacific Time on our Discord server; stay tuned to our Mastodon feeds for details, or subscribe to this calendar. We'd love to have you join us, as we always love to hear from new speakers!

Next Episodes

Oxide and Friends

Data Visualization @ Oxide and Friends

📆 2024-03-15 16:41 / 01:25:52


Oxide and Friends

Crucible: The Oxide Storage Service @ Oxide and Friends

📆 2024-02-14 16:45 / 01:38:40


Oxide and Friends

Innovation Stagnation? @ Oxide and Friends

📆 2024-02-07 16:45 / 01:00:44


Oxide and Friends

Helios @ Oxide and Friends

📆 2024-02-01 16:45 / 01:47:50


Oxide and Friends

What's taking so long?! @ Oxide and Friends

📆 2024-01-24 16:00 / 01:35:10