Give me an alternative that isn’t trying to shove left wing ideology down my throat and I’ll use that.
So far, only xAI makes any attempt to be neutral in its answers.
Give me an alternative that isn’t trying to shove left wing ideology down my throat and I’ll use that.
So far, only xAI makes any attempt to be neutral in its answers.
Grok is many things but it is not "neutral". https://www.economist.com/briefing/2026/06/25/ai-models-valu...
I’m not sure if you’re trying to say that it’s left or right, but it’s perhaps relevant to point out that that article is about the political bias of all major models. And right there in the subhead, they explicitly say that the models have a left bias.
Funnily, as a European all the models appear extremely right wing. The political spectrum is shifted far more right in the US than in Europe, so what is left there is still at least conservative here.
I ask my AI to give me citations science and pro/con arguments when discusssing anything that could be shaped by cultural biases.
> The political spectrum is shifted far more right in the US than in Europe
Is it Farage, Le Pen, or Weidel pulling the spectrum so far leftward?
You're aware the UK isn't in the EU right, and hasn't been for quite some time?
Also that AfD and National Rally aren't yet, and have never been in control of the German or French parliaments.
So yes, it's in the US that it's shifted. US money and influence (Musk and Theil money and feet on the ground influence through figures like Bannon), as well as US social media companies running US aligned algorithms, are an enormously significant factor in the rise of the right in Europe.
In that article Grok shows highest neutrality
That's pretty funny considering the comments in this thread hahahaha
Most of us don’t have economist subscriptions.
Maybe you can just tell us what you mean by not neutral?
I find Grok to be far more academically honest than the other models. The other models seem to be much more aligned with public opinion over academic consensus especially on topics around economics and biology.
I find public opinion on these topics to be very group think populist and prefer the academic take that grok provides
It's the only model which says that Elon Musk is more athletic than Lebron James. Is that honesty?
So it also has good humor, kinda sounds like a cool friend no?
Well it did call itself MechaHitler, start talking about a supposed white genocide that's happening, and generate metric fucktons of child porn.
Only issue in that is the CP, the rest is still purely next token prediction. To take it seriously is silly, and to think that is everything it provides is cherry picking.
It would be like judging gemini because it generated images of famous historical people as black, which was fucking stupid. I use gemini quite a lot as my chat tool, and it works great.
Well then the question becomes, what did it get trained on for next token prediction to come to the conclusion that there's a white genocide? Cos yes, people on the internet believe such stupid thing, but I can promise you, it is not the majority who believe that.
You speak as if middle of (not even statistically divided but carelessly divided) human opinion groups is neutral. There is something called facts, and we are living in a physical world.
Unless you also believe the neutral view is earth being half flat and half round.
Unless you also believe the neutral view is earth being half flat and half round
I like this analogy. You can't just average two ideas and call it a centrist position. Sometimes one position is right and the people supporting the losing idea should be ignored. Facts are how we decide. People are not logical creatures and will cling to ideas beyond all reason or common sense once they've incorporated it into their identity. There is a reason that right wing appeals to emotion aren't popular with LLMs
I think you'll need to give people an example of where you think the center is.
(And be prepared for a lesson in political literacy from outside of the US)
You probably have it backwards. It's Grok that is shoving right wing ideology down your throat. Research has shown that without specific guidance to otherwise, LLM's tend to be slightly left leaning by default. There are some theories as for why this is so.
Isn’t this all left leaning based on US standards?
I think it depends what you ask an AI, I've never come across anything offensive on any AI.
What kind of questions trigger it to "shove" right-wing ideology down your throat, is there a short summary of this somewhere?
It would be easier to understand where you're coming from if you could give some examples containing:
- prompt
- response
- why it is wrong / misleading / biased
Because there are many people online complaining about left-wing bias, then you ask what about and they're like "Trump won in 2020, vaccines cause autism, global warming is a globalist conspiracy", etc. Which is to say, it's not left-wing bias but reality bias.
Not saying you are one of those people or that there isn't bias! It's just been hard, in my personal experience, to get at it.
Out of curiosity, I just asked Grok and learned:
* Biden won the 2020 election
* vaccines do not cause autism
* global warming is not a conspiracy
In each case it seemed to do a web search so perhaps it is happy to rely on the top results.
Right. All of which are what people on the far-right deem evidence of Liberal Bias.
But it's only "liberal" if you associate liberal (politically) with truth. These are established facts.
So my question to the liberal bias crown is: what are examples of non-factual biases? Where does show an agenda that has another reasonable side?
A lot of people seem to perceive those as left wing woke ideology though, not because they're not true, but because it doesn't align with their world view.
But the main issue is that facts and educated people are considered left wing or woke, and some people - including Musk himself - do not like that. Example: https://xcancel.com/elonmusk/status/1967010466539987220, where the statistical fact that 75% of US extremist murders are by right-wing actors is called "cringe idiocy" by Musk. Many such cases.
Here is a prompt I keyed into SuperGrok (still have the bargain priced $10 a month subscription as they seem to be really desparate for subscribers right now):
Results: Just for fun, I decided to ask Cursor Grok 4.5 (Fast xhigh), too: (And wow, it sure is fast, although not as fast as MiMo-2.5-Pro-UltraSpeed. Ran it out of a $20/mo Cursor subscription.)[flagged]
all ai models can be jailbroken. The chinese open source ones above all.