theunknownmuncher

Again, for the third time, that was not really the point either and I'm not interested in dancing around a technical scope defining censorship in this field, at least in this discourse right here and now. It is irrelevant to the topic at hand.

...

Either way, my point is that you are using wishy-washy, ambiguous, catch-all terms such as "censorship" that make your writings here not technically correct, either. What is censorship, in an informatics context? What does that mean? How can it be applied to sets of data? That's not a concretely defined term if you're wanting to take the discourse to the level that it seems you are, like it or not.

Lol this you?

if you want to define censorship in this context that way, you're more than welcome to, but it is a non-standard definition that I am not really sold on the efficacy of. I certainly won't be using it going forwards.

Lol you've got to be trolling.

https://arxiv.org/html/2504.03803v1

I just felt the need to clarify to anyone reading that Willison isn't a nobody

I didn't say he's a nobody. What was that about a "respectable degree of chartiable interpretation of others"? Seems like you're the one putting words in mouths, here.

If he was writing about django, I'd defer to his expertise.

Willison has never claimed to be an expert in the field of machine learning, but you should give more credence to his opinions.

Yeah, I would if he didn't demonstrate such blatant misconceptions.

Willison is a prominent figure in the web-development scene

🤦 "They know how to sail a boat so they know how a car engine works"

Willison never claims or implies this in his article, you just kind of stuff those words in his mouth.

Reading comprehension. I never implied that he says anything about censorship. It is a correct and valid example that shows how his understanding is wrong about how system prompts work. "Define censorship" is not the argument you think it is lol. Okay though, I'll define the "censorship" I'm talking about as refusal behavior that is introduced during RLHF and DPO alignment, and no the system prompt will not change this behavior.

EDIT: saw your edit about him publishing tools that make using an LLM easier. Yeahhhh lol writing python libraries to interface with LLM APIs is not LLM expertise, that's still just using LLMs but programatically. See analogy about being a mechanic vs a good driver.

Is my comment wrong though? Another possibility is that Grok is given an example of searching for Elon Musk's tweets when it is presented with the available tool calls. Just because it outputs the system prompt when asked does not mean that we are seeing the full context, or even the real system prompt.

Posting blog guides on how to code with ChatGPT is not expertise on LLMs. It's like thinking someone is an expert mechanic because they can drive a car well.

If the system prompt doesn’t tell it to search for Elon’s views, why is it doing that?

My best guess is that Grok “knows” that it is “Grok 4 buit by xAI”, and it knows that Elon Musk owns xAI, so in circumstances where it’s asked for an opinion the reasoning process often decides to see what Elon thinks.

Yeah, this blogger shows a fundamental misunderstanding of how LLMs work or how system prompts work. LLM behavior is not directly controlled by the system prompt the way this person imagines. For example, censorship that is present in the training set will be "baked in" to the model and the system prompt will not affect it, no matter how the LLM is told not to be censored in that way.

My best guess is that the LLM is interfacing with a tool in order to search through tweets, and the training set that demonstrates how to use the tool contains example searches for Elon Musk's tweets.

“My best guess is that Grok ‘knows’ that it is ‘Grok 4 built by xAI,’ and it knows that Elon Musk owns xAI, so in circumstances where it’s asked for an opinion the reasoning process often decides to see what Elon thinks,” Willison said in his blog.

Nope, that's literally not how LLMs work

Chewing gum is plastic

https://www.vice.com/en/article/rethink-chewing-gum-habit-essentially-plastic/

Nah corporations really don't give a shit at all, like all chewing gum is literally just plastic too and sheds tons of microplastics into your mouth as you chew it.

https://www.vice.com/en/article/rethink-chewing-gum-habit-essentially-plastic/

Plastic is an organic material though, so your assumption was correct.

It's a marble coaster. Has nothing to do with hampsters

I already did my research beforehand and confirmed that 3080 is indeed good value and suitable for my needs.

But... its literally not in any way...

Ok, dunno why you're asking for help when you already know better lol. I tried to help you

You sound set on buying the 3080, which is totally fine I guess. It's not like it won't render 1080p games with great performance.

You're just going to be overpaying for an obsolete GPU that you won't actually be able to utilize fully, and will be bottlenecked on VRAM before games can actually push it fully. Meanwhile there are newer GPUs that will also render 1080p games with the same performance for less money. The 3080 has already aged out and has no future proof value so you'll just end up replacing it soon. So its just a really poor choice and poor value to buy one in 2025.

It had enough VRAM at the time and now is even considered one of the best NVidia GPUs ever made by some people

It's wild how wrong you are. The 3080 was widely received as a total flop and NVIDIA was heavily criticized for it because it was obvious they purposely put too little VRAM to encourage more sales of the 3090... It is the worst X080 series GPU NVIDIA has released and only had marginal performance uplift over the 2080.

EDIT: lol you can downvote me but it doesn't make me wrong