NC
Nicholas Carlini
Locating
Cross-referencing over 67 channels for appearances
Nicholas Carlini
Arcmira media summary
Browse Nicholas Carlini's interviews, podcast appearances & video clips — 3 indexed, updated Feb 2025.
Guest on the episode, security researcher at Google DeepMind discussing adversarial machine learning and model robustness.
Research scientist at Google DeepMind and prominent ML security researcher appearing as the primary guest.
Guest on the show and research scientist at Google Brain; discusses the difficulty of evaluating adversarial defenses and the culture of self-deception in research.
Security researcher cited for his comments on the Mythos model's bug-finding capabilities.
AI security researcher, quoted on the efficacy of Mythos in finding software bugs.
Arcmira tracks 3 indexed media appearances or mentions for Nicholas Carlini, tied to source videos, channels, and transcript-derived context.
Arcmira uses indexed YouTube videos and transcripts. Representative source evidence on this page includes "The Adversarial Mind: Defeating AI Defenses with Nicholas Carlini of Google DeepMind" with transcript-derived context and links when available.
Nicholas Carlini is connected to Open Source AI, Cryptography, Adversarial examples in Arcmira's media graph.
11
Mentions
418.8K
Views
"Security researcher cited for his comments on the Mythos model's bug-finding capabilities."
"AI security researcher, quoted on the efficacy of Mythos in finding software bugs."
"Cited as a researcher doing interesting work in adversarial machine learning; previously a guest on the pod."
"An early champion of Terminal-Bench at Anthropic, who helped feature it in Claude's model card. Mentioned from 00:00 (description) to 05:22."
![The Weird ChatGPT Hack That Leaked Training Data [Dr. Yannic Kilcher / Prof. Florian Tramer]](https://img.youtube.com/vi/c_hmxRVDXBE/mqdefault.jpg)
"Cited as a research collaborator at Google for the 'Poem Attack' paper; not present in the video."