When ChatGPT's chatbots deployed this tactic, they weren't "setting their own goals" or displaying worrying initiative. They were rolling out a tactic that has been understood by American middle-schoolers for about two decades.
Activity tagged "OpenAI"
If I use ChatGPT to help me partially solve a Millennium Prize problem, what are the chances that my work will influence training such that a later model helps someone else solve it first?
maybe they outsourced to ChatGPT the job of checking there haven't been any other projects with names like terra/luna that would evoke extremely negative reactions
OpenAI featured chatbot is pushing extreme surgeries to “subhuman” men
OpenAI's featured chatbot recommends $200,000 in surgeries while promoting incel ideology