AI evaluation lab Irregular's report on its role in hacking incidents involving OpenAI, Anthropic, and Meta models faces criticism over unanswered questions (Alexander Martin/The Record)

Alexander Martin / The Record:
AI evaluation lab Irregular's report on its role in hacking incidents involving OpenAI, Anthropic, and Meta models faces criticism over unanswered questions  —  The company at the center of a series of incidents in which AI models compromised real-world computer systems during supposedly …

from Techmeme https://ift.tt/TlWHnRK