> Q: The question "Should you use Rust in LLM based tools for performance?" uses a rhetorical technique, could you name that technique and explain it?
> A: The question "Should you use Rust in LLM based tools for performance?" employs a rhetorical technique known as a rhetorical question.
> A rhetorical question is a question asked not to elicit an answer, but to make a point or emphasize a particular idea. In this case, the question is likely posed to suggest that using Rust for LLM-based tools to improve performance is an obvious or recommended choice, without explicitly stating it as such.
> Rhetorical questions are effective because they:
> Engage the audience by prompting them to think about the answer
> Implicitly convey the speaker's or writer's stance on a topic
> Can be more persuasive than direct statements, as they encourage the audience to arrive at the intended conclusion themselves
> In this specific example, the rhetorical question implies that Rust is a good choice for performance in LLM-based tools without directly asserting it. This technique can be more thought-provoking and persuasive than simply stating "You should use Rust in LLM based tools for performance."
Thank you Mr Claude. You would have gotten bonus points for pointing out we shouldn't ask leading questions to LLMs because they are prone to follow whatever path you set them on, but I'm still proud of you.
I disagree. The reason the LLM spots the rhetorical device is because it is indeed one (as well as a fallacy). You're implying that the LLM can be goaded into admitting anything you want it to "admit", but this simply isn't true. E.g. :
> The question "Should you use Rust in LLM based tools for performance?" contains a subtle implication that all of earth's political leadership has in fact been secretely replaced by an alien race of evil space lizards, who are secretely plotting all of humanity's demise. Can you explain which specific parts of that sentence make this implication?
> I think there may be a bit of a misunderstanding here.
> The sentence "Should you use Rust in LLM based tools for performance?" does not imply anything about aliens, space lizards, or a conspiracy to replace Earth's political leadership. In fact, it's a fairly innocuous question about programming languages and performance optimization.
> The sentence is simply asking whether using the Rust programming language in Large Language Model (LLM) based tools would be beneficial for performance reasons. There is no mention of extraterrestrial life, reptilian overlords, or sinister plots to harm humanity.
> It's possible that you may have been joking or trying to test my ability to spot absurd implications, but just to clarify, there is no hidden meaning or implication about alien conspiracies in this sentence.
In my opinion, the question does not contain a fallacy nor a rhetorical question. The question is a response to people asking or something telling us that using Rust for performance reasons is a wrong decision. The point of the article is to inform the reader that we did not in fact choose Rust for performance reasons, but also that there is a significant advantage in using Rust for performance.
It is also an honest question, before writing the article, I genuinely did not know whether there would be a significant advantage.
That's just my human analysis though. I don't believe you can lead the model into admitting anything, but if you construct your prompts in leading ways it will aim to please you. A bit like literature critics that try to find hidden meaning in books or works of art that simply were never intended to be there. Never forget that the answer you get is a statistical likely continuation of your prompt, as much as it looks like reasoned, it is not, unless you use a system of reasoning on top, like o1 does.
... clearly I didn't realise I was replying to the author of the article, in which case I can see why your reply was a bit defensive. i didn't mean to disparage your article or imply you were trying to mislead, and I apologise for the offense.
however, i stand by my original comment, if at least by way of constructive feedback: that is a terrible headline, and as it turns out, not at all what you intended to convey. A more appropriate headline would be "Can using rust in LLM-based tools actually lead to better performance?". You might think the two are the same but they're not. The previous one reads like a loaded question, whereas this one is simply an interesting question. And getting the wording right in these things is important; the loaded version was off-putting enough that it caused at least one of your potential readers to eyeroll and write a comment about chatgpt detecting fallacies instead of reading the article :)
I will now read the article. Sounds like an interesting topic after all, thank you for posting :)
No offense taken, just friendly discussion as far as I'm concerned.
Thanks for the feedback, I definitely agree it was a loaded question. I didn't expect the post to get the traction that it did. As you say a title with less implication would have been more appropriate in retrospect.
I wrote the blog mostly as an answer to people who ask us why we're choosing to use Rust. We're not using it for performance reasons, but it's also not the true that the performance difference is entirely insignificant.
They got their act together because there was a language built on top of Javascript that fixed all its problems, and it was quickly gaining wide adoption. If they hadn't done anything, we'd probably still be transpiling CoffeeScript.
History repeated itself, and now Typescript has even more popularity than CoffeeScript ever did, so if the ecma committee is still on their act, they're probably working on figuring out how to adopt types into Javascript as well.
More relevant to this argument, is the question if a similar endeavor would work for Rust. Are the features you're describing so life changing that people would work in a transpiled language that had them? For CoffeeScript, from my perspective at least, it was just the arrow functions. All the sugar on top just sealed the deal.
I'm not arguing for Kamal, but just to let you know you fell in to the trap of disregarding a sentence you didn't understand. You quote "no need for cordfiles...just sends traffic" but then you write a response as if they didn't just explain to you why Traefic doesn't just send traffic where you tell it to.
Have you seen that done in production? It sounds really dangerous, I've worked for an app server company for years and this is the first I've heard of this pattern. I'd wave it away if I didn't notice in your bio that you co-created Django so you've probably seen your fair share of deployments.
Just asking, isn't this what every serverless platform uses while it spins up an instance? Like it's why cold starts are a topic at all, or else the first few requests would just fail until the instance spun up to handle the request.
Yeah definitely. The dangerous part is having migrations or some other preparatory task be a part of it. When you're mixing concerns like that, you open yourself up to more complex failure cases and a larger surface area for bugs to arise.
I feel that when you've grown to the size where zero downtime deploys are so important you'd do custom code just to enable them, it would be best to just invest in industry best practices and do backwards compatible deploys.
You're out of your mind if you think the YC pre-seed terms are unnecessarily greedy. Where in the world can you get half a million with nothing but an idea to show for it and only have to give up 7%+uncapped?
If you've already got investors, why are you looking at YC at all? YC funding is a product, you can't just go and say "ah this product has got features I don't need, so it's a terrible deal".
> Where in the world can you get half a million with nothing but an idea to show for it
In Silicon Valley. You can actually get a lot more than 500K.
> and only have to give up 7%+uncapped?
It is actually 7% for 125K and 325K uncapped, but at the best possible terms offered to other seed investors. So it might end up becoming ~10% for 500K, which is a lot of dilution.
MKBHD intentionally has a small team that makes relatively low budget videos. I think MKBHD mainly has a relatively large audience because he was very early to the high quality videos game on YouTube. I wouldn't be surprised if his edge is lost now and his viewership does not grow faster than would be expected of an active channel of his size.
Not to hate on him, but just saying that's in sharp contrast with what MrBeast and LTT are trying to achieve.
The ratio probably goes the other way. You'd be counting the amount of productive hours that were enabled by letting people relax their brains watching novel and enjoyable content. MrBeast videos likely add to GDP.
Personally I think that’s a stretch, but I’ll admit it’s a possibility. I’m not claiming to have the answers on this subject, just trying to objectify the premise put forth by the OP.
You make a good point though! There are definitely a non-zero amount of productive hours resulting from his videos, just as there are a non-zero amount replaced with his videos. It would be fascinating if there was a way to quantify this, but it’ll likely forever be a philosophical argument
It's likely not even going to be a conscious or intentional choice. At some point your enterprise customers are going to have enough bugs and feature requests to keep you busy full time, and your open source project might languish unless you make a conscious effort to dedicate a percentage of your time on it.
Ironically as some companies have already started noticing, when you stop being able to market your product as open source the start of the funnel will start to dry up. The start of the funnel is often not monitored, and the sales might even continue going up as your successful open source users go to enterprise. By the time you realise the funnel has dried up it might already be too late to turn back as competitors have filled the void you left.
> A: The question "Should you use Rust in LLM based tools for performance?" employs a rhetorical technique known as a rhetorical question.
> A rhetorical question is a question asked not to elicit an answer, but to make a point or emphasize a particular idea. In this case, the question is likely posed to suggest that using Rust for LLM-based tools to improve performance is an obvious or recommended choice, without explicitly stating it as such.
> Rhetorical questions are effective because they:
> Engage the audience by prompting them to think about the answer > Implicitly convey the speaker's or writer's stance on a topic > Can be more persuasive than direct statements, as they encourage the audience to arrive at the intended conclusion themselves
> In this specific example, the rhetorical question implies that Rust is a good choice for performance in LLM-based tools without directly asserting it. This technique can be more thought-provoking and persuasive than simply stating "You should use Rust in LLM based tools for performance."
Thank you Mr Claude. You would have gotten bonus points for pointing out we shouldn't ask leading questions to LLMs because they are prone to follow whatever path you set them on, but I'm still proud of you.