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!
No persons identified in this episode.
This episode hasn't been transcribed yet
Help us prioritize this episode for transcription by upvoting it.
Popular episodes get transcribed faster
Other episodes from Oxide and Friends
Transcribed and ready to explore now
A Half-Century of Silicon Valley with Randy Shoup
24 Feb 2025
Oxide and Friends
Holistic Engineering with Robert Mustacchi
23 Jan 2025
Oxide and Friends
Crates We Love
16 Jan 2025
Oxide and Friends
Predictions 2025
10 Jan 2025
Oxide and Friends
OxF 2024 Wrap-Up
30 Dec 2024
Oxide and Friends
Scaling Bluesky with Paul Frazee
19 Dec 2024
Oxide and Friends