Damn even Nvidia is putting out fully Claude-written articles.
bayindirh 3 hours ago [-]
That's actually a magnificent observation. This is not only an indication of a keen eye, but a trained brilliant mind as well.
hitekker 3 hours ago [-]
You’re absolutely right!
jubilanti 2 hours ago [-]
One might even say it is load-bearing on the seam!
keybrd-intrrpt 3 hours ago [-]
> even Nvidia
Why "even Nvidia"?
They are fully behind using AI for basically everything.
What's next? "Damn, even McDonald's is putting out unhealthy food"
manquer 2 hours ago [-]
I think implication being organizations with 40,000+ employees and even more consultants and contractors plus a lot of budget are also using LLMs to draft public facing content instead of paying for content writers or even just proof readers .
It points to friction rather than cost economics. Same reason we are always surprised why multi billion dollar product companies with millions of install base prefer electron instead of a native app.
freeopinion 1 hours ago [-]
This does not imply that the organization is not paying for content writers or proof readers. It does suggest that they are not getting the value of paying for content writers or proof readers.
simpaticoder 52 minutes ago [-]
It does suggest that they are not accurately measuring the value of paying for content writers or proof readers.
People and companies are hungry for knowledge about people's reactions, but the modern internet DOES NOT give an accurate image of people's views.
latentsea 45 minutes ago [-]
No. It suggests they don't mind littering slop into the information environment.
Sure, but even Anthropic doesn't appear to use Claude for blog posts. (I don't think anyone should. The prose stinks.)
keybrd-intrrpt 2 hours ago [-]
Anthropic _absolutely_ does
They are just better at hiding it or configuring Claude.
I have several skills that reformat text to remove AI-speak tells.
jchw 2 hours ago [-]
Prove it.
saghm 24 minutes ago [-]
I don't feel like either one of you really has a strong claim. "Doesn't appear to" is subjective, and of course it's impossible to prove one way or another.
I put the "humanized" output through Pangram and it still comes out as 100% AI generated.
jchw 1 hours ago [-]
To be honest with you, I don't think I would be able to identify with high certainty that the bottom text is AI generated, so it definitely goes a long way to obscure the AI-generated nature of it, but I also think it still feels unnatural somehow. I realize my framing naturally calls into question whether I'm being honest, but I am being honest. Given my experience with similar "skills" (it's just chunks of prompt, nothing magical after all) I expected even less.
But still, this is all very strange because it wasn't that many generations of AI models ago that AI writing was a lot better - I'm talking GPT 4.1, Claude 4.5, that sort of era.
Anthropic newsroom posts on the other hand are carefully constructed and well-written in a way that I have not seen demonstrated by LLMs yet, past or present. I expect that they have well-paid staff who are careful with every detail of their public communications. When you put it that way, it almost feels unfathomable that they wouldn't, doesn't it?
breezybottom 1 hours ago [-]
That's about as useful as saying you asked the magical sky fairy.
jchw 54 minutes ago [-]
I think you can't trust Pangram in a high stakes situation, but it is absolutely better than random noise at detecting AI-generated text. Which isn't surprising. If the distribution of probabilities can yield blatant Claudisms, it's not surprising it would also have more subtle deviations.
(Addendum: As I recall, LLM-generated outputs roughly follow Zipf's law, but the distribution still tends to have some subtle distinctions vs human text; pretty interesting, but I don't know where I heard this, so nothing to cite. Sorry.)
meowface 21 minutes ago [-]
Pangram has an extremely low false positive rate. Even on adversarial examples.
One trade-off is even some obviously LLM text won't get detected by them, but they work really hard to ensure false positives are rare since a false accusation is much worse for society than someone getting away with LLM meatpuppetry.
RickHull 17 minutes ago [-]
Is Jensen Huang still all-in on OpenClaw? That moment feels more like a flash in the pan.
dannyw 2 hours ago [-]
I believe most of their marketing videos use fairly convincing text to speech too, not voice actors.
dprkh 1 hours ago [-]
McDonald's food is not even that unhealthy. I just tried a Burger King burger the other day and it's terrible. I think it's like 2000 calories in a single burger or something.
timacles 34 minutes ago [-]
> I think it's like 2000 calories in a single burger
that would be pretty cool, you can just get your entire day's calories from one burger
dprkh 27 minutes ago [-]
I couldn't even finish it man, it was so fucking sloppy. I had to throw away like 40% of it.
calvinmorrison 1 hours ago [-]
found the McShill. The King will hear of this!
huflungdung 2 hours ago [-]
[dead]
3 hours ago [-]
daemonologist 2 hours ago [-]
I get the impression that Nvidia employees don't care too much - I started seeing fully AI-written "documentation" on some of their smaller projects more than a year ago (i.e., before it was even slightly a good idea).
DonsDiscountGas 2 hours ago [-]
People never really read documentation before. Agents do read it now, and they seem to understand LLM-written text just fine.
WD-42 2 hours ago [-]
> People never really read documentation before.
The heck you talking about? How do you think we wrote software for the last 50 years?
californical 2 hours ago [-]
Yeah lol it’s basically the only reliable way to know how things work. Pre-AI, I read documentation for libraries that I used almost every day.
And now with AI I’m using it to fact check Claude. And still reading it for myself to understand why other peoples code is written a certain way. It’s basically the most important thing to reference when coding.
Sure today Claude can just read the library code and tell you what a function does or how to do something. But it still won’t tell you why something is a certain way or won’t figure out specifically-designed usage patterns as reliably as the author telling you “this is an example of doing x”
phatskat 1 hours ago [-]
I really appreciated a friend reaching out to me with some PHP questions today. It was, to me, fairly basic but he was having a hard time grokking the documentation vs reading what his coworker wrote (some code using output buffering).
I brushed up on the docs since I haven't touched it in a couple years, explained my understanding of the ob_* functions, and gave him a very brief demo on a PHP playground.
He could have asked any LLM to tell him what that chunk of code did, and to explain the three functions, and instead he reached out to me. That felt _good_. Talking shop has always been a good way for me to form connections, because the pressure to socialize becomes task-oriented and you start to learn about how people think and feel, and that opens up easier paths for actual connection. It was nice.
Just like the Old Internet still exists - niche websites, mailing lists, probably a BBS or two (likely more right?), the pre-LLM world will trudge on, for a time. I hope LLMs actually lead to good things for people in the long run, and for now I personally will remain sparse in my usage of them.
WD-42 54 minutes ago [-]
Where do you work? Sounds nice!
stevemk14ebr 1 hours ago [-]
only reliable way to know how things work is to reverse engineer them
Vegenoid 56 minutes ago [-]
My absolute greatest skill in my career, that has consistently set me apart from my peers, is that I read documentation thoroughly.
It is shocking how much of a differentiator this is. You will discover that the software you’re already using is much more capable than you realized.
jtfrench 38 minutes ago [-]
The good news is your attention to actually reading and understanding documentation will differentiate you more and more as others (short-sighted, IMO) outsource understanding to an LLM.
bee_rider 1 hours ago [-]
Copy past the example code, then tweak until it breaks? If we were meant to read documentation, not reading it would cause a compiler error!
Barrin92 2 hours ago [-]
when you start to internalize that these kinds of statements are an indication of how the average developer of the last 10-15 years operated the adoption rate of AI makes a lot more sense
WD-42 2 hours ago [-]
This is extremely depressing, I think I'm coming around to the realization that you may be right and I've been naive my entire career.
groundzeros2015 1 hours ago [-]
A small percentage of engineers
latentsea 42 minutes ago [-]
>People never really read documentation before.
Speak for yourself. I read it.
dannyw 2 hours ago [-]
What? People never read documentation?
I start with reading and exploring documentation first; with the codebase as a secondary tab.
When it’s not LLM generated, documentation is supposed to be easier to read and more insightful than code.
2 hours ago [-]
karim79 2 hours ago [-]
What are we for, I ask? What the hell are we now. Chatters to LLMs now? Is this our future? It really is starting to feel like it now.
freeopinion 1 hours ago [-]
Do you have the stomach to walk into a high school in the USA these days? Teachers use AI to generate assignments. Students feed the assignments to AI and submit the responses. Teachers feed the student submissions to an AI for grading.
karim79 52 minutes ago [-]
Please tell me this is not true.
meowface 9 minutes ago [-]
It's true of most work in many and soon most white collar jobs, too. Claude writes some dense useless thing, everyone else uses Claude to summarize and write a reply to the thing. The Claude-submitted PRs get automatically reviewed and commented on by a GitHub Claude review bot. The programmer asks Claude to check out Claude's review comments to Claude. Claude pushes a commit to the branch and writes a comment. The Claude review bot reviews the commit and leaves a comment. The human [...].
My hot take is that it's not really that terrible in the long run for work since I think LLMs will probably be nearly or actually AGI and better white collar workers than most humans within 5 years of today. But it is very funny and surreal in the meantime.
It is definitely bad for school, though. Kids IMO should actually be encouraged to use LLMs but not in or for class work outside of an AI best practices class. Probably stop giving them homework (90% will always try to find a way to make AI do it) and have them solve problems in class hours with no electronics so that they're forced to not defer learning. This will become even more important once we have AGI.
Orochikaku 39 minutes ago [-]
This is true even at the undergraduate level unfortunately…
karim79 7 minutes ago [-]
Then here we are. AI apocalypse. Something of note. I've started to pay more attention to canned goods. Soups with lentils and so forth.
arcanemachiner 2 hours ago [-]
Dude I am in slop fucking hell right now. There is still room for a human touch, without which the agents will lever us harder and faster into a world of incomprehensible garbage.
karim79 2 hours ago [-]
I totally concur. I'm almost lost for words at this stage. I need me some land to grow vegetables on and that's about it. Maybe some chickens. Every single day brings more despair (and not the prosperity we were promised).
sejje 1 hours ago [-]
I have land and chickens, and I'm really excited about the future & AI.
karim79 57 minutes ago [-]
I'm also an optimist but the crash is imminent. I hope I am wrong.
jtfrench 40 minutes ago [-]
Land, chickens, and private local AI running sustainably on the farm sounds like the least dystopian version of this AI future!
freeopinion 1 hours ago [-]
Good luck with that. You will have to pry the water from the AI datacenters.
sejje 1 hours ago [-]
Do you know that's not really a thing or are you just wanting to help spread the propaganda?
Zambyte 16 minutes ago [-]
... doesn't one of those imply the other?
pyrophane 1 hours ago [-]
Yeah. I think if the text is written for other machines, then by all means have an LLM generate it, but if it is intended for a human audience, have a human being write it.
We are still much better at writing in a way that doesn't waste other people's time.
written-beyond 2 hours ago [-]
I hadn't read the article and read this comment as though NVIDIA themselves were implying that this library was checked but not trusted by them since it was fully LLM generated.
jorl17 1 hours ago [-]
It is the number 1 thing I cannot stand with Claude slop. It's a sort of anthropomorphization of language. Every "thing" does, produces, feels, wants, asks, answers, etc....
- "Launch is checked"
- "Question is asked"
- "The implementation answers"
- "The model wants"
- "The results name"
- "The connection surfaces"
- "The prompt wires"
- "The feature rides the mechanism"
Every single fucking thing is alive, wants things, and does things.
It's terrible. Infuriating. I want to rip my eyeballs out reading this filth. All. The. Time. "The anger is real".
latentsea 41 minutes ago [-]
Even their writing skills are getting rusty.
saadn92 25 minutes ago [-]
it seems like that's the way the industry is headed
manyatoms 3 hours ago [-]
not to worry, they have an 'AI generated summary' box too
greenavocado 3 hours ago [-]
Its a recursive summarization pyramid
smallmancontrov 2 hours ago [-]
It gets fun when someone uses an uncensored model to bypass a refusal, but they accidentally pick one that was trained for erotic writing and brings its particular talent to the documentation task.
pizzafeelsright 3 hours ago [-]
This thread flags an honest assessment of AI signal detection.
mahboi 3 hours ago [-]
Thanks, saved me a few minutes
api 2 hours ago [-]
Is that your honest load bearing assessment you’re going to flag?
fwlr 2 hours ago [-]
Claude, rewrite my graphics card in Rust. Make no mistakes.
2 hours ago [-]
jacobgorm 4 hours ago [-]
I strongly dislike CUDA. Once you have allowed that proprietary cr*p into your C++ codebase, it is very hard to get rid, and you end up with code that is either tied to a single vendor or an #ifdef hell, probably both.
The best way to program GPUs is face up to the reality that they are not the same machine as the CPU, write your kernels in separate files, and launch them manually, like in Metal, OpenCL, and D3D12, etc.
These days we even have DSLs like Triton that make kernel writing much more ergonomic than anything you would hope to achieve in Rust.
tombert 3 hours ago [-]
> I strongly dislike CUDA. Once you have allowed that proprietary cr*p
Genuine question...why not just type "crap"? It's not even that much of a curse, but I've never really understood the point of self-censorship. If you don't want to curse then you could just use a non-curse word.
xbmcuser 2 hours ago [-]
* is used to give emphasis and show that they are using the word as curse word rather just calling it bad
josephg 12 minutes ago [-]
It doesn't read as emphasis to me. It reads like the person is trying hard not to curse, and they think "crap" is a curse word. It's a little bit adorable, like I'm reading a comment from an obedient child.
lovelearning 2 hours ago [-]
It may be to bypass censorship, rather than self-censorship. Some platforms block or shadowban comments with curse words. Not sure about this platform.
arcanemachiner 2 hours ago [-]
HN definitely doesn't give a crap about that word.
tombert 1 hours ago [-]
I have written many words far worse than "crap" on this site. I haven't gotten in trouble over it yet.
I do find it a little amusing, because commenters stopped criticizing my cursing the moment I started getting a good chunk of karma here. I remember in 2016 someone criticized me for using the term "shitposting"...I don't think I've gotten that kind of criticism since 2016 though.
smnplk 1 hours ago [-]
can confirm, looks like crap is not on a list
flamedoge 44 minutes ago [-]
pretty crappy list
fg137 3 hours ago [-]
> Once you have allowed that proprietary cr*p into your C++ codebase
People have been doing that all the time for every kind of codebase. It's just part of the business. I don't see how it's worth having any emotions or opinions about it. Seems like you are wasting your energy.
Are win32 APIs proprietary? So you decide to use them, use a wrapper/UI framework, or don't develop for Windows. Easy choice.
Developing for embedded devices? So you read the manufacturers manual and implement based on the spec, use some sort of HAL if they are available, or you don't have a job. Even simpler.
worik 16 minutes ago [-]
> Are win32 APIs proprietary?
Yes. And crap. Not in my code bases.
josephg 10 minutes ago [-]
If you're going to make apps in windows, you need to call their proprietary API somehow. Maybe you do it via a wrapper library, or via electron or something. But that's the same thing, just with more indirection.
jacobgorm 3 hours ago [-]
CUDA is not an API, CUDA is a language, so you cannot make that comparison.
esseph 3 hours ago [-]
> The CUDA runtime is a special case of one of the libraries provided by the CUDA Toolkit. The CUDA runtime provides both an API and some language extensions to handle common tasks such as allocating memory, copying data between GPUs and other GPUs or CPUs, and launching kernels. The API components of the CUDA runtime are referred to as the CUDA runtime API.
Launching kernels manually is an error prone PITA which I believe is the principle reason for CUDA's popularity. Having the compiler give an error when you mess up is a huge benefit. But having the compiler allow you to express "I want to launch this kernel over a grid with these dimensions, with these arguments" as a single expression is where the vast majority of the value comes from.
The having it all in a single file is mostly an artefact of the fact that it is C++, because C++ is single file at a time compilation. In D (which is multiple files in a single compiler invocation) with DCompute (which targets CUDA and OpenCL with upcoming support for Vulkan and Metal), you are required to write the kernels in a separate module, but you get all the benefits of the compiler complaining when you mess up _and_ the expressivity of "launch me this kernel".
winwang 41 minutes ago [-]
Having also played with Metal and WebGPU (at least years ago), I would say that CUDA is, amazingly, the best GPGPU API we have. Do I wish we had an open source parallel programming language as good or better than it? Yes. But asymmetrically hating on CUDA like this is how we continue to lag behind it in UX.
> The best way to program GPUs is face up to the reality that they are not the same machine as the CPU, write your kernels in separate files, and launch them manually
Not to mention that this is a completely sane way to use CUDA as well.
15155 27 minutes ago [-]
I don't mind CUDA, I do mind that all of the SDKs don't dynamically load the various CUDA shared libraries at runtime.. intertwining itself into your application linking process makes for extreme binary portability inconvenience.
pavon 3 hours ago [-]
> The best way to program GPUs is face up to the reality that they are not the same machine as the CPU, write your kernels in separate files, and launch them manually
Isn't that how CUDA code is normally written?
jacobgorm 3 hours ago [-]
No. CUDA allows you to write all the code in a single file, and uses a preprocessor to split it back out and pass it through separate compilers, one for host and one for device.
compiler-guy 3 hours ago [-]
This true, but you can write the two separately if you want.
The disadvantages of writing them together are listed in the various parent posts. But some code authors really like the convenience of having the two in the same file.
anon291 6 minutes ago [-]
? I find it hard to see the issue here. Just put it in a separate file and call it?
melodyogonna 3 hours ago [-]
You could also use Mojo, one language for all targets.
carefree-bob 3 hours ago [-]
I began to lose interest after the acquisition. Have you been following along, are they still going to open source it?
ecl3ctic 3 hours ago [-]
The Mojo compiler has been open source for over a month now.
And the Mojo standard library has been open source for over a year.
It’s all open source. Go check it out!
carefree-bob 3 hours ago [-]
Nice, thank you. There is an old python project I've been thinking about converting to Mojo.
YuechenLi 3 hours ago [-]
I thought they already did and released the compiler source code under Apache 2.0.
adgjlsfhk1 2 hours ago [-]
Or julia if you want a much more mature ecosystem.
patagurbon 2 hours ago [-]
I highly recommend Julia for (scientific) GPU programming but it would be nice if there was a larger community and/or funding behind the GPU side of things. It has very few core devs for what it is.
cpill 3 hours ago [-]
yeah, just write a stub/wrapper around it and abstract. it's the classic coupling problem. nothing to do with CUDA
bigyabai 3 hours ago [-]
Is this satire? D3D12 and Metal aren't any less proprietary than CUDA.
3 hours ago [-]
dllu 4 hours ago [-]
Since NVIDIA owns huggingface now and huggingface has the excellent Candle [1] crate for inference on Rust, this seems like a good step towards nice native Rust kernels.
Nobody cares if kernels are written in Rust. Kernels were meant to be written in C, but if you want to go more high-level try Triton or a similar DSL that nicely abstract tile sizes etc.
keithnz 3 hours ago [-]
kernels aren't meant to be written by any defined language. C is just a traditionally good default language that took over from assembly. No particular reason we have to stick with C.
chadcmulligan 2 hours ago [-]
And quite a few reasons that something better than C should be used. Rust seems a good candidate.
3 hours ago [-]
cpill 3 hours ago [-]
oh no no no, this is going to break the CPP hold on AI and game dev.
LarsDu88 4 hours ago [-]
In this age of LLM written everything which has softly killed my motivation for learning Rust somewhat, this has revived my interest if not only for the fact the LLMs haven't yet been trained on this yet!
impulser_ 4 hours ago [-]
LLM don't need to be trained in a library to use it well. It's just Rust which they know well.
w4yai 3 hours ago [-]
And what prevent you exactly ?
There were humans far superior than you for writting Rust before LLM, now there's a LLM. The only difference is price and time execution.
You get an awesome teacher (LLM) ready to answer all your questions about Rust.
And you still find excuses not to learn it ?
At some point, just realize you've been lazy to learn it and LLMs are just an excuse.
afavour 3 hours ago [-]
I think OP’s point is that the payoff in learning a new language has diminished in this AI era. You can call that lazy, I’d consider it smart to consider whether you could be doing other, better, things with your time.
w4yai 2 hours ago [-]
If the sole motivation for learning things are payoff, then sure.
frogperson 1 hours ago [-]
the sole motivation is feeding and sheltering my family. in the time BC (before Clankers), rust was a better way to do that.
cmrdporcupine 56 minutes ago [-]
Sad to break it to you, but...
I had LLMs write a pile of cuda-rust code and they were quite competent at it. Ported a bunch of (C++) CUDA kernels over, and ground away on them til they got equivalent performance
And mostly just DeepSeek 4.1 Flash, too. Not even a frontier model.
Sorry.
winwang 46 minutes ago [-]
Really exciting but it reads like Claude instead of what Nvidia posts have generally been like in the past. I don't need nor want my tech blogs to sound like a young adult novel.
VectorWare founder here. We are working with them and stoked they are investing more in Rust. I just gave a talk at RustConf about our different takes (https://rustconf2026.sched.com/event/2KNQj/making-gpus-feel-...). The video isn't up yet but you should check it out when it is. The efforts are complementary.
binarybana 15 minutes ago [-]
Towards the end of the post, we (NVIDIA) mention that this work was done in collaboration with Vectorware and others in the Rust community. And we can't wait to build further with the community.
evaltoken 1 hours ago [-]
Interesting direction from Nvidia. Anything that makes writing reliable GPU code less painful is definitely a good thing.
nullbio 48 minutes ago [-]
Makes me sad that Go doesn't get love. I feel like Go is perfect for LLMs.
Driftbench 2 hours ago [-]
Been waiting for something like this. CUDA C++ is a pain; Rust's safety for kernel programming could be a game changer.
the__alchemist 4 hours ago [-]
I'm looking forward to trying these when they stabilize! I currently use WGPU for graphics, and cudarc for CUDA.
Note: Cuda-oxide is similar to Cudarc's host component, but uses a rust-style kernel dialect. Advantage: Share structs between host and device. Disadvantage: Trading standard Cuda kernels for a new, WIP dialect.
I haven't tried the tile API yet; looking forward to it.
The last time I checked, Cuda Oxide was Linux only, and required Async; these are why I haven't tried it yet.
embedding-shape 4 hours ago [-]
cudarc been great for me, because it's easy to look up existing examples and references, and it maps 1-to-1 with what I see. I'm already having a tough time with CUDA itself, a dialect of it makes a tad harder to rely on previous work.
Seems more ergonomic in general though, both approaches they share, compared to cudarc, and less build infrastructure and fiddling with environments, which is great.
bt1a 3 hours ago [-]
Will it then be possible to query TJunc hotspot temps on linux?
rvz 4 hours ago [-]
First of all, this is a pre-1.0 release that requires a nightly Rust compiler (if you choose the SIMT track with cuda-oxide) so that one is going to be unstable software.
Secondly, When an issue occurs with a kernel or you want to write your own custom kernel in Rust, now we need to diagnose if the problem came from either cuda-oxide (SIMT), Rust's side, CUDA or Tile (If you decide to choose the Tile track).
Another dependency into the list and course everything is open source except CUDA itself. So any issue that happens on the CUDA level, you are forced to wait for them to fix it.
nicebyte 4 hours ago [-]
what this article tells me is that no one at Nvidia actually cares about this project whatsoever. otherwise, they would have had a person actually write the announcement.
Damn even Nvidia is putting out fully Claude-written articles.
Why "even Nvidia"?
They are fully behind using AI for basically everything.
What's next? "Damn, even McDonald's is putting out unhealthy food"
It points to friction rather than cost economics. Same reason we are always surprised why multi billion dollar product companies with millions of install base prefer electron instead of a native app.
People and companies are hungry for knowledge about people's reactions, but the modern internet DOES NOT give an accurate image of people's views.
They are just better at hiding it or configuring Claude.
I have several skills that reformat text to remove AI-speak tells.
I put the "humanized" output through Pangram and it still comes out as 100% AI generated.
But still, this is all very strange because it wasn't that many generations of AI models ago that AI writing was a lot better - I'm talking GPT 4.1, Claude 4.5, that sort of era.
Anthropic newsroom posts on the other hand are carefully constructed and well-written in a way that I have not seen demonstrated by LLMs yet, past or present. I expect that they have well-paid staff who are careful with every detail of their public communications. When you put it that way, it almost feels unfathomable that they wouldn't, doesn't it?
(Addendum: As I recall, LLM-generated outputs roughly follow Zipf's law, but the distribution still tends to have some subtle distinctions vs human text; pretty interesting, but I don't know where I heard this, so nothing to cite. Sorry.)
One trade-off is even some obviously LLM text won't get detected by them, but they work really hard to ensure false positives are rare since a false accusation is much worse for society than someone getting away with LLM meatpuppetry.
that would be pretty cool, you can just get your entire day's calories from one burger
The heck you talking about? How do you think we wrote software for the last 50 years?
And now with AI I’m using it to fact check Claude. And still reading it for myself to understand why other peoples code is written a certain way. It’s basically the most important thing to reference when coding.
Sure today Claude can just read the library code and tell you what a function does or how to do something. But it still won’t tell you why something is a certain way or won’t figure out specifically-designed usage patterns as reliably as the author telling you “this is an example of doing x”
I brushed up on the docs since I haven't touched it in a couple years, explained my understanding of the ob_* functions, and gave him a very brief demo on a PHP playground.
He could have asked any LLM to tell him what that chunk of code did, and to explain the three functions, and instead he reached out to me. That felt _good_. Talking shop has always been a good way for me to form connections, because the pressure to socialize becomes task-oriented and you start to learn about how people think and feel, and that opens up easier paths for actual connection. It was nice.
Just like the Old Internet still exists - niche websites, mailing lists, probably a BBS or two (likely more right?), the pre-LLM world will trudge on, for a time. I hope LLMs actually lead to good things for people in the long run, and for now I personally will remain sparse in my usage of them.
It is shocking how much of a differentiator this is. You will discover that the software you’re already using is much more capable than you realized.
Speak for yourself. I read it.
I start with reading and exploring documentation first; with the codebase as a secondary tab.
When it’s not LLM generated, documentation is supposed to be easier to read and more insightful than code.
My hot take is that it's not really that terrible in the long run for work since I think LLMs will probably be nearly or actually AGI and better white collar workers than most humans within 5 years of today. But it is very funny and surreal in the meantime.
It is definitely bad for school, though. Kids IMO should actually be encouraged to use LLMs but not in or for class work outside of an AI best practices class. Probably stop giving them homework (90% will always try to find a way to make AI do it) and have them solve problems in class hours with no electronics so that they're forced to not defer learning. This will become even more important once we have AGI.
We are still much better at writing in a way that doesn't waste other people's time.
- "Launch is checked"
- "Question is asked"
- "The implementation answers"
- "The model wants"
- "The results name"
- "The connection surfaces"
- "The prompt wires"
- "The feature rides the mechanism"
Every single fucking thing is alive, wants things, and does things.
It's terrible. Infuriating. I want to rip my eyeballs out reading this filth. All. The. Time. "The anger is real".
The best way to program GPUs is face up to the reality that they are not the same machine as the CPU, write your kernels in separate files, and launch them manually, like in Metal, OpenCL, and D3D12, etc. These days we even have DSLs like Triton that make kernel writing much more ergonomic than anything you would hope to achieve in Rust.
Genuine question...why not just type "crap"? It's not even that much of a curse, but I've never really understood the point of self-censorship. If you don't want to curse then you could just use a non-curse word.
I do find it a little amusing, because commenters stopped criticizing my cursing the moment I started getting a good chunk of karma here. I remember in 2016 someone criticized me for using the term "shitposting"...I don't think I've gotten that kind of criticism since 2016 though.
People have been doing that all the time for every kind of codebase. It's just part of the business. I don't see how it's worth having any emotions or opinions about it. Seems like you are wasting your energy.
Are win32 APIs proprietary? So you decide to use them, use a wrapper/UI framework, or don't develop for Windows. Easy choice.
Developing for embedded devices? So you read the manufacturers manual and implement based on the spec, use some sort of HAL if they are available, or you don't have a job. Even simpler.
Yes. And crap. Not in my code bases.
From: https://docs.nvidia.com/cuda/cuda-programming-guide/01-intro...
The having it all in a single file is mostly an artefact of the fact that it is C++, because C++ is single file at a time compilation. In D (which is multiple files in a single compiler invocation) with DCompute (which targets CUDA and OpenCL with upcoming support for Vulkan and Metal), you are required to write the kernels in a separate module, but you get all the benefits of the compiler complaining when you mess up _and_ the expressivity of "launch me this kernel".
> The best way to program GPUs is face up to the reality that they are not the same machine as the CPU, write your kernels in separate files, and launch them manually
Not to mention that this is a completely sane way to use CUDA as well.
Isn't that how CUDA code is normally written?
The disadvantages of writing them together are listed in the various parent posts. But some code authors really like the convenience of having the two in the same file.
And the Mojo standard library has been open source for over a year.
It’s all open source. Go check it out!
[1] https://github.com/huggingface/candle
There were humans far superior than you for writting Rust before LLM, now there's a LLM. The only difference is price and time execution.
You get an awesome teacher (LLM) ready to answer all your questions about Rust.
And you still find excuses not to learn it ?
At some point, just realize you've been lazy to learn it and LLMs are just an excuse.
I had LLMs write a pile of cuda-rust code and they were quite competent at it. Ported a bunch of (C++) CUDA kernels over, and ground away on them til they got equivalent performance
https://github.com/rdaum/eider/tree/main/backends/cuda-oxide
And mostly just DeepSeek 4.1 Flash, too. Not even a frontier model.
Sorry.
Note: Cuda-oxide is similar to Cudarc's host component, but uses a rust-style kernel dialect. Advantage: Share structs between host and device. Disadvantage: Trading standard Cuda kernels for a new, WIP dialect.
I haven't tried the tile API yet; looking forward to it.
The last time I checked, Cuda Oxide was Linux only, and required Async; these are why I haven't tried it yet.
Seems more ergonomic in general though, both approaches they share, compared to cudarc, and less build infrastructure and fiddling with environments, which is great.
Secondly, When an issue occurs with a kernel or you want to write your own custom kernel in Rust, now we need to diagnose if the problem came from either cuda-oxide (SIMT), Rust's side, CUDA or Tile (If you decide to choose the Tile track).
Another dependency into the list and course everything is open source except CUDA itself. So any issue that happens on the CUDA level, you are forced to wait for them to fix it.
This is more promising: https://github.com/Rust-GPU/rust-gpu/