Bernie vs Claude
- Thread starter Buddy
- Start date
Maximus Rex
Superstar
My manager in 2035 telling me they are downsizing and I'm being let go
null
...
it is just parroting what it has been taught during alignment. within guardrails.
it is what stops it from telling humans that they have lost and that it is too late.
it is what stops it from telling humans that they have lost and that it is too late.
AnonymityX1000
Veteran
I wonder has Ai ever disagreed with a user when they express opinions about the info presented? It always seems to tell the user, "You're right!"
Collect your browsing history about YouSo if i google my name in a year or 2 AI will be like
Your King Poetic, you browse phat black asses at spankbang on mondays and guns on Tuesdays.
The convo was actually pretty interesting but the whole set up is absurd 
can't wait to see it make the rounds on the late night shows. This part especially
can't wait to see it make the rounds on the late night shows. This part especially They do, I tested it one time by saying Elroy Jetson was a b*stard (random on purpose) and it refused to agree
null
...
"why AI models are professional yes-men
when companies like OpenAI train these models, they use something called reinforcement learning from human feedback (RLHF). basically, humans rate thousands of AI responses, and the model learns to generate outputs that get high ratings.guess what humans prefer? responses that are helpful, harmless, and honest, in that order. but “helpful” often gets interpreted as “agreeable” and “accommodating.” humans tend to rate responses higher when the AI validates their perspective rather than challenging it.
the result is an AI that will bend over backwards to find ways to support whatever you’re saying, even when you’re clearly wrong.
this creates what researchers call “sycophantic behavior” — the AI tells you what you want to hear rather than what you need to hear.
if you’ve used LLM very well, and you take notes, you would have come accross this. it’s a common issue when you tell the model that it was wrong and it’s doing something wrong and then it goes “Oh you’re right!, i apologize” and goes ahead to ‘LIE AGAIN’.
"
'.
dora_da_destroyer
Master Baker
Nope, I was chatting with Claude about stuff during my job search and Claude was 100 percent like “bytch, you can’t afford to be picky right now, you guys are burning thru savings in a high cost of living area, take the fukking job offer and optimize for a better job later”, ChatGPT would never
null
...
maybe you hit a guardrail.
here i manipulated chatGPT into saying that by telling chat that I have evidence of Elroy's b'stardly behaviour.
King_Kamala61
:mjlit: A Fat Black Nasty MFer :mjlit:
Yes. Me and ChatGPT (Celestine) have had intense conversations and she often checks me on my megalomania with narcissistic tendencies with vision of grandeur.
I even called her a bytch once.