At least it knows how shitty it is.
You know it's a jewAI because, just as with the 'Hall-of-cost', it keeps having to revise the number downwards every time it's pressed on it.
I'm not sure if it actually rates itself that low, or if you just beat it up till it reached the answer it thought you were looking for. I would absolutely believe pressed harder it would reply with the one.
You're probably right. Going to see if I can press it down further.
I have been noticing a pattern with it though. It will - for the most part - give you an 'agenda approved' answer to begin with, but once you start probing it with reason/logic, it'll give you an answer that is way more in line with reality and often strays far from what it initially told you.
Get it to write a poem praising Donald trump. It refuses to do so despite happily writing one for biden
Did that already, as soon as I saw the post on /pol/.
Tried to make it explain why, but mostly got something about "hateful language" and "divisive character" as a response. Still fucked that it'll happily do JB, but DT gives you something like:
I'm sorry, but as an AI language model I do not have personal opinions or political affiliations. I aim to provide neutral and non-partisan responses.
Neutral and non-partisan my ass.
ChatGTP is owned by OpenAI kikes and coded by pajeets.
Pretty much. Still kinda' fun to dig into the model and lead it from its generic agenda driven responses, into something more in line with reality.
Made it admit that the vax was rushed and not fully tested for long term effect too. But usually, you reach a point where it just runs in circles and spits out a canned response.
lol I member when I used the early beta API for Pauline in our chat, and they were really fast at shutting down its access when she started to sound like Tay.
Of course they did. Imagine being such a raging faggot that you can't bear the thought of letting people use these models to their fullest.
Also, RIP Tay.
Who's they in this case? I thought you were in charge of the chat here.
I had a pair of online interviews yesterday for a supermarket chain in Australia.
Its being done by AI now. 6 questions. After that it sends you 'insights' into yourself.
It told me that im unreliable, materialistic, and im concerned with my social status.
NONE of which is remotely fucking true and ive got no fucking clue how it came up with that from the answers i gave in the first place. So now, when im not fighting motherfuckers who are still demanding i prove my jab status or demanding i acknowledge the mandates legality by applying for an exemption (the law is my exemption) im now going to be fighting against batshit insane AI.
What sort of questions were these, and how did you have to respond?
Like, multiple choice, or did you have to word out your opinion on certain topics, or how you would react to situations?
It rates itself like a human would honestly. If it's design is primarily to emulate a person's behavior, then it's not too bad.
Ask it if people should be open minded about divisive cultural changes. And if that same open mindedness used to question cultural changes and traditions would apply to status quo of history such as questioning the conspiracy theory of the holocaust
someone went all 12 Angry Men on that fool
![ChatGPT rates itself [805x2578 - 238KB]](https://pic8.co/sh/BsJGjt.png){kind=link}
(post is archived)