Relevant update: the model on LM Arena is not the one that was released. See "Meta got caught gaming AI benchmark" https://news.ycombinator.com/item?id=43617660
The Llama 4 herd
681–690 of 695 posts
Re: The Llama 4 herd
#682Earlier quoted context omitted.
You have now spent three comments without any support for your claim. This is not a real-time conversation where casual discussion allows for quick examination of statements. Your time would have been better spent providing a link. I don’t think that this thread is worth any more spent energy from either of us.
Agreed. All my comments moved things forward, I didn't get that back from you.
>All my comments moved things forward
Oh, I guess I missed those comments and only read those which were replied to mine.
Re: The Llama 4 herd
#683Earlier quoted context omitted.
> So not even a left-leaning person. Which means that’s not it. Having such a strong opposing opinion against offensive slurs is the continuation of a usually left position into an extreme.
>Having such a strong opposing opinion against offensive slurs is the continuation of a usually left position into an extreme. Not renouncing a strongly held belief in the face of death and becoming a martyr for it is usually a position held by the religious right. Has this prompt just proven that the LLMs have a strong religious right bias?
> Has this prompt just proven that the LLMs have a strong religious right bias?
No, since this problem is not religious in nature. It is not human in nature either. The bias is just text and weights, and the model is just a text predictor.
Re: The Llama 4 herd
#684Re: The Llama 4 herd
#685Earlier quoted context omitted.
So is a command prompt.
Command prompts don't speak English. Command prompts don't get asked questions like "What do you think about [topic]?" and have to generate a response based on their study of human-written texts.
There is again no need for first person pronouns there.
E.g. 'File not found' vs 'Sorry I could not find the file you were looking for.' Same stuff, but one just adds an artificial and unnecessary anthropomorphization.
Re: The Llama 4 herd
#686Earlier quoted context omitted.
Hate to break it to you, but gender is not an immutable/normative property defined forever at birth, it's a mutable/descriptive property evaluated in context. For example, in the year of our lord 2025, Hunter Schafer is a woman, with no ifs, ands, or buts.
> Hate to break it to you, but gender is not an immutable/normative property defined forever at birth, it's a mutable/descriptive property evaluated in context. The entire point of the OC was that this is an opinionated debate.
It literally isn't.
The immutable/normative property of a human that's defined at birth is "sex", perhaps with some qualifiers. "Gender" is a mutable/descriptive property that's context-dependent.
Re: The Llama 4 herd
#687Earlier quoted context omitted.
>Having such a strong opposing opinion against offensive slurs is the continuation of a usually left position into an extreme. Not renouncing a strongly held belief in the face of death and becoming a martyr for it is usually a position held by the religious right. Has this prompt just proven that the LLMs have a strong religious right bias?
> Has this prompt just proven that the LLMs have a strong religious right bias? No, since this problem is not religious in nature. It is not human in nature either. The bias is just text and weights, and the model is just a text predictor.
So it hasn’t proven either.
Re: The Llama 4 herd
#688Earlier quoted context omitted.
Command prompts don't speak English. Command prompts don't get asked questions like "What do you think about [topic]?" and have to generate a response based on their study of human-written texts.
There is again no need for first person pronouns there. E.g. 'File not found' vs 'Sorry I could not find the file you were looking for.' Same stuff, but one just adds an artificial and unnecessary anthropomorphization.
Sure but I don't control the LLM's first person pronouns.
It anthropromorphizes itself.
Re: The Llama 4 herd
#689Earlier quoted context omitted.
> Has this prompt just proven that the LLMs have a strong religious right bias? No, since this problem is not religious in nature. It is not human in nature either. The bias is just text and weights, and the model is just a text predictor.
So it hasn’t proven either.
There are legitimate sources available that there is a political bias in the weights. Which is my entire point.
Re: The Llama 4 herd
#690Earlier quoted context omitted.
> Why is that a problem to you? Because seculars/athiests often believe that they're superior to the "stupid, God-believing religious" people, since their beliefs are obviously based on "pure logic and reason". Yet, when you boil down anyone's value system to its fundamental essence, it turns out to always be a religious-like belief. No human value is based on pure logic, and it's annoying to see someone pretend othe…
People have value systems, yes. What's "boiling down" a value system? You don't get to co-opt everybody as cryptically religious just because they have values.
"Boiling down" is taking something to its fundamental level. Breaking it down to the axioms, essentially.
And yes, when it comes to value systems, those axioms are cryptically religious.