

HackTalk: Boyd Kane
HackTalk: Boyd Kane
Boyd is a technical AI safety researcher in the MATS 9 Extension, working with Alex Turner (Google DeepMind) and Alex Cloud (Anthropic) on methods to detect deceptively misaligned AI. He previously wrote embedded software for satellites at CubeSpace, interned at AWS in Cape Town, and holds an MSc in Computer Science from Stellenbosch University.
His talk: “Uncovering public traces of the OpenAI Huggingface incident”. Shortly after the incident was announced, Boyd found the datasets and scripts used by OpenAI’s agent swarm to attack Hugging Face; the talk goes through how the agents took over Hugging Face.
Format: 15-30 min talk + 10-15 min Q&A. Online (Zoom); the Zoom link is shown once you RSVP.
Part of the AI Incident Response Sprint, September 11-13, online. Co-organized by Apart Research and CeSIA, the French Center for AI Safety.