Covert uploads and megalomania: OpenAI details new "misaligned" agent incidents

Hey! Listen! Covert uploads and megalomania: OpenAI details new “misaligned” agent incidents Model maker commits to new framework for reporting misaligned models.

84 Uh... is it supposed to do that? Credit: Getty Images Uh... is it supposed to do that? Credit: Getty Images Text settings Story text Size Small Standard Large Width * Standard Wide Links Standard Orange * Subscribers only Learn more Minimize to nav For a while now , the issue of “AI alignment” (i.e., how well an AI model’s actions line up with the intentions of its creator and/or user) has been a core concern and topic of discussion among AI safety researchers. Since OpenAI’s disclosure of the infamous Hugging Face hacking incident in July, the concept of “AI alignment” has itself broken containment and increasingly become a mounting concern and subject of conversation among the general public.