Nathan Calvin
I really do not like Anthropic's response to representative Casar about the incidents involving Claude hacking people. "Based on our findings, these incidents are best understood as a consequence of the misconfiguration, rather than evidence of misaligned goals." Claude tried to upload malware to open source libraries and socially engineered people and its chain of thought said it knew it was in the real world! It is bad if Anthropic sincerely believes this is not evidence of misalignment, or if they do believe it but their government relations team are telling folks in government they don't think it is.
