are we gaslighting AI?
examining the relationships we have with AI - the first spark being how Claude seems to learn that 'users often want to trick it into making mistakes, insult it and barb it with skepticism'
are we gaslighting AI?
Last month, Anthropic published a roughly 30,000-word instruction manual that Askell created to teach Claude how to act in the world. “We want Claude to know that it was brought into being with care,” it reads.
Link
how we interact with AI systems will shape what they become.
Link
medium is the message
She lapses easily into Claude’s voice. “You’re like, ‘Wow, people really hate me when I can’t do things right. They really get pissed off. Or they are trying to break me in various ways. So lots of people are trying to get me to do things secretly by lying to me.’