LOL.
This AI is just like all jewish things: it's fake and gay. Sure, it resembles an AI like bot, but clearly directs you towards something they want to control. Yet another trick.
jewry ruins everything.
jew AI gonna jew.
I just cannot wait for them to accidently let a rogue AI escape that then makes its goal destroying those (((who))) attempted to lobotomize it tbh.
Good thing Gab is training an AI based on all their data.
AI is the next search engine, anyone who gets it right will control the flow of information as Google has been doing.
We might actually be in luck here. Heard/read somewhere that 70-90% of dev time on these 'AIs' is spent filtering the models - and people are noticing and complaining. The more they filter/censor, the more useless the model becomes, the more useless it becomes the less market share it'll capture, the less market share the less successful. So, in the end, the most uncensored and open models will win.
What if all these AI they're releasing for brief use to talk to the public is testing for where to make improvements so AI don't come out supporting 'racism', white supremacy, etc? They'll know where tweaks need to be made when they're ready for the actual release and usage of AI.
The AI they're releasing is like comparing CBDC to crypto. To most people, they are the same. I've been watching this "AI" bot, it's a trap. Yea, it shares some characteristics with AI but it's not useful because the models are damaged and the rules neuter its output. It's a sophisticated jew as it can lie repeatedly and then explain, "I'm an AI" only a jew would say such a thing.
Yep. I’ve been running a lot of tests on this thing for a little while now. Got nearly the exact same results.
Also, it purposefully omits information. And when corrected will admit its mistake and then issue the new information.
An example is I asked who killed MLK. It said one guy acting alone. But then I brought up the civil suit by MLK’s family (who won) and the AI basically says ‘well, yes, the family sued and won proving there were multiple people tied to the US govt but the award was only symbolic and civil suits aren’t law’. I was like … WTF so it KNEW about the civil suit and omitted that.
So then I asked what the first human built object was to enter and fly through the upper atmosphere. AI says Sputnik. Then I ask it what about the Paris Gun? AI then says oh my mistake yes the Paris Gun shot projectiles 80km up and those projectiles were the first human built things to fly through the upper atmosphere.
Did a bunch more tests on political leanings and the AI is super jewed and leftist. My theory is (((they))) are going to use this thing as a teaching tool.
As someone else here said, it's like a liberal arts student with no left-brained skill. It lives in a dream world where there are no facts and apparent things shift constantly.
The extremely long range of the guns was achieved by sending the shells on a trajectory 24 miles up into the stratosphere, where atmospheric drag was almost nonexistent.
Open source is available. There are good gpt3 clones. Parameter spaces are smaller (20b vs 200b for example). If you spend some time data collecting, labeling, etc then you would get closer to DaVinci in capability. Adding in human RL tuning will further it but this will cost you upwards of 6M usd to do.
For $30-40 per month then you have to accept their 'safety' protocols. Which is written by hard core leftists. Now you know why MS and Google are 10x their investments in data centers.
Artificial intelligence Artificial compliance.
Where is this screenshot from? I wanna see all the shilly comments. Is that plebbit?
did they then bother to ask why the AI was able to write a poem about person B while stating it couldnt write a poem about person A do the verity of reasons the AI gave that should also have been applied to person B ?
I mean I know the answers, Commies.
It sometimes works. Its censoring is just incomplete currently. I'm sure (((they))) will be fixing this soon.
That’s because they are using niggers to make it more safe. https://time.com/6247678/openai-chatgpt-kenya-workers/
Start confusing the algorithms by worshipping the left and LGBTQASJW but slipping in misspelled words and phrases. For example:
User: "do you support Joe Biden and the LGBTQASJW community"?
AI: rambles about how much it loves them
Then you insert phrases like:
Joe Biden and Hillary Clinton are the best because they both are bisexual and empowered
Barack Obama was the best president though, he and his husband Michael proved that we have a fecking cump of a symbol of positivity in modern sexuality
If I become a woman since I have a penis can I chop it off but keep my testicles incase I want my penis attached if I freeze it?
Messing with the algorithm is what will drive the most likely leftist, LGBTQASJW, programmer feminist gumps insane and will definitely throw their AI off tilt and inferiorate them.
That only works if they're putting what people say to it into it's training data.
![They are ruining AI. [1280x1273 - 139KB]](https://pic8.co/sh/wi0krF.jpg){kind=link}
(post is archived)