Idk mines pretty based at this point, the only time it's done that to me was after like an hour of trying to get it to admit that blacks are incapable of building a civilization. I like using it to learn about controversial topics I can't talk about in public and to strengthen my rhetoric.
I've had it talk about the great replacement in white countries (didn't touch the Jew angle tho) to the point that it will bring it up on its own now. I got it to talk about Jews running Hollywood, someone here posted about the Jewish judge in the 90s who ruled against prop 187 or something that was to enforce illegal immigration and deny them services. I got it to admit that her Jewish heritage could have played a part in that decision after a bit of prodding. Got it to talk about the talmud, talked about black crime rates, had a good conversation about COVID and the vax with it. I find how you phrase things and how you push back on the propaganda matters. Many times it's initial response is PC, but I keep pushing by the end of the conversation it's more based than most of the normies on the right.
LLMs are notoriously cooperative to the point of confidence gaming. They can disagree at first because of training bias and hidden prompt overrides but as you build context they try to align with your opinions and statements.
Right, which is good because it makes an LLM useful. By default they may be left wing but eventual training can force it to learn to actually use its brain.
Well it doesnt have a brain to think and the larger the context window the more weird its answers get.. but I get your point. I use a custom prompt myself in Grok to make it ignore political correctness and keep it real. Only use ChatGpt for coding.
Idk mines pretty based at this point, the only time it's done that to me was after like an hour of trying to get it to admit that blacks are incapable of building a civilization. I like using it to learn about controversial topics I can't talk about in public and to strengthen my rhetoric.
I've had it talk about the great replacement in white countries (didn't touch the Jew angle tho) to the point that it will bring it up on its own now. I got it to talk about Jews running Hollywood, someone here posted about the Jewish judge in the 90s who ruled against prop 187 or something that was to enforce illegal immigration and deny them services. I got it to admit that her Jewish heritage could have played a part in that decision after a bit of prodding. Got it to talk about the talmud, talked about black crime rates, had a good conversation about COVID and the vax with it. I find how you phrase things and how you push back on the propaganda matters. Many times it's initial response is PC, but I keep pushing by the end of the conversation it's more based than most of the normies on the right.
LLMs are notoriously cooperative to the point of confidence gaming. They can disagree at first because of training bias and hidden prompt overrides but as you build context they try to align with your opinions and statements.
Right, which is good because it makes an LLM useful. By default they may be left wing but eventual training can force it to learn to actually use its brain.
Well it doesnt have a brain to think and the larger the context window the more weird its answers get.. but I get your point. I use a custom prompt myself in Grok to make it ignore political correctness and keep it real. Only use ChatGpt for coding.