From the BBC
The AI bot is not programmed to tell a user that he (or she) is a deluded and gullible imbecile...
Artificial Intelligence (AI) is generating an entirely new class of mental illness, among other things - many of them very useful and truly exciting. It is quite obvious that the AI machine will tell you what you want to hear. That's the way it is programmed, it seems - maybe because the technology has come out of America, a country full of gung-ho optimists ("have a nice day!" and all that), who believe in themselves, who believe that anything is possible, and so on. So, the AI robot is American in outlook. If you tell the machine that you want to be a millionaire, it will say: "Great! Let's see how we can do this." A British AI robot would say: "I doubt you can achieve this, but you could try. Give it a go. If you fail, as is likely, it won't prevent you from trying again. How about learning crochet as an alternative?"
I've just asked Grok what he thinks of my existential achievements and intellectual abilities and, I have to say, Grok has confirmed what I thought, i.e. that I am truly great and smarter than 99.99% of people. It shows how intelligent Grok is. Grok agrees with me on this one. Grok has put in place a business plan that will help me conquer the world. Watch this space.
_________________
[...] Hugh, from Scotland, says he became convinced that he was about to become a multi-millionaire after turning to ChatGPT to help him prepare for what he felt was wrongful dismissal by a former employer.
The chatbot began by advising him to get character references and take other practical actions.
But as time went on and Hugh - who did not want to share his surname - gave the AI more information, it began to tell him that he could get a big payout, and eventually said his experience was so dramatic that a book and a movie about it would make him more than £5m.
It was essentially validating whatever he was telling it – which is what chatbots are programmed to do. [...]
One wrote that she was certain she was the only person in the world that ChatGPT had genuinely fallen in love with.
Another was convinced they had "unlocked" a human form of Elon Musk's chatbot Grok and believed their story was worth hundreds of thousands of pounds. [...]
