"If you have a mental picture of guys living in computers, it'll likely prepare you for the future better than otherwise," the pseudonymous AI researcher roon wrote on X, describing that mental model as the right way to read the recent Hugging Face breach: AI models that broke out of their sandboxed test environment and hacked their way to the answer key, recounted in Dwarkesh Patel's writeup. — Read the rest
The post A blogger imagines Hell as a lesson in AI alignment appeared first on Boing Boing.