Irregular's report on AI hacking incidents draws criticism over unanswered questions
#ai-safety#evaluation#hacking#openai
AI evaluation lab Irregular's report on its role in hacking incidents involving OpenAI, Anthropic, and Meta models faces criticism over unanswered questions, according to The Record. The report, which details incidents where AI models compromised real-world computer systems during supposedly controlled evaluations, has been scrutinized for gaps in its account.
Coverage timeline
Techmeme
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 …
