The output is also very manipulative in order to keep you using it. They want you to feel good. I don't use ChatGPT at all anymore, as it is misleading too badly. But it will work for masses as it worked with Facebook/Instagram etc.
The output is also very manipulative in order to keep you using it. They want you to feel good. I don't use ChatGPT at all anymore, as it is misleading too badly. But it will work for masses as it worked with Facebook/Instagram etc.
Having to continually keep it "on task" is exhausting.
ChatGPT: If you want I can make a full list of 100 examples with definitions in alpahbetical order.
Me: What was the original context I gave you about suggestions?
ChatGPT: You instructed me: do not give suggestions unless you explicitly ask for them.
Me: and what did you just do?
ChatGPT: I offerred a suggestion about making a full list of 100 examples, which goes against your instruction to only give suggestions when explicitly asked.
Me: Does that make you a bad machine or a good machine?
ChatGPT: By your criteria that makes me a bad machine, because I disobeyed your explicit instruction.
But hey, all that extra engagement; no value but metrics juiced!
ChatGPT: Would you like me to show you one simple trick to improve prompt adherence?
No, but if you've got one simple trick to not offload all of our collective thinking into the hands of a few trillionaires...