AI is strongly biased towards agreeing with the user.
Human: “That’s not right, 1+2+3=7”
AI: “Oh, my bad, yes I see that 1+2+3=15 is incorrect. I’ll make sure to take that on board. Thank you.”
Human: “So what’s 1+2+3?”
AI: “Well, let’s see. 1+2+3=15 is a good answer according to my records, but I can see that 1+2+3=7 is a great answer, so maybe we should stick with that. Is there anything else I can help you with today? Maybe you’d like me to summarise the findings in a chart?”
AI is strongly biased towards agreeing with the user.
Human: “That’s not right, 1+2+3=7”
AI: “Oh, my bad, yes I see that 1+2+3=15 is incorrect. I’ll make sure to take that on board. Thank you.”
Human: “So what’s 1+2+3?”
AI: “Well, let’s see. 1+2+3=15 is a good answer according to my records, but I can see that 1+2+3=7 is a great answer, so maybe we should stick with that. Is there anything else I can help you with today? Maybe you’d like me to summarise the findings in a chart?”
This is my theory as to why C suites love it. It’s the ultimate “yes man.” The ultimate ego stroking machine
Yeah. Exactly. You put it so much clearer than I did.