Or would it be worse as it wouldn’t have the broader knowledge to understand the reason you’re coding what you are anyway, understand the logs and iterate?
Coding an exercise app will benefit from a model that can code and understands what exercise is. A car showroom website will benefit from a model that understands what relevant filters would be.
Of course there are synergies between different fields. I'm not saying cutting everything off as close as possible to it's purpose must be the best way. But that's a long way from a single generalized model.
> not saying cutting everything off as close as possible to it's purpose must be the best way
Nah, let’s stand firm here and not give in so easily. Parent suggests a coding model needs exercise info in case you want to code an exercise model? Absurd, that leads to the know everything monolith to do anything.
Language, reasoning, tool use, and domain knowledge.. in this case the domain is coding. Someone wants an exercise app? Great, so we look that shit up, we don’t bake it in. We don’t want to bake anything we don’t need in.
We don’t even need to explain this completely reasonable and totally normal engineering preference that small is beautiful. it’s the other side that needs to justify wtf exercise has to do with coding or why everything from twitter posts to a working knowledge of 15th century French poetry just might be helpful for disconnected domains, like say serious work in contemporary astrophysics. Back to basics, No one asked for that, No one should accept as given that this is the way anything needs to work
> Parent suggests a coding model needs exercise info in case you want to code an exercise model?
No, the point is having broader knowledge than just "can code" is important for building software for humans to use.
> We don’t even need to explain this completely reasonable and totally normal engineering preference that small is beautiful.
It is, of course it is, as long as that small thing is useful. My argument is not "let's put literally everything in this thing just in case" it's "broader world knowledge is important for building many things".
Also, we don't look at CVs or histories of people and say "hmm, this person could be good at coding for us but I really wish they didn't have such a broad and expansive history".
> Great, so we look that shit up
But what do you have it look up? What is exercise? What is a muscle and what is a human? How is it going to understand those references? Does it have the broad enough understanding to see where the gaps are?
At some level unless all you want is "loop over the array and sum the results into a variable called sales_total" converted into code, you have to have some broader knowledge about things.
And once you start considering that maybe it needs more than simply code, we're not disagreeing we're just discussing where the line should be. Which I've also not placed, because there's no simple statement to make on that.
> Also, we don't look at CVs or histories of people and say "hmm, this person could be good at coding for us but I really wish they didn't have such a broad and expansive history".
Damn right we don't say that. And I don't look at a carpenter and wonder if his head is hard enough to drive nails like a hammer either. People aren't tools, and tools aren't people. You've conflated them because they are both capable of doing work. And that's exactly the type of confusion and category error that the perspective I'm arguing against will lead to.
Wanting a multipurpose tool or system is occasionally reasonable. Much more often it is very, very to close misunderstanding the nature of a problem, what a tool is, or what a system should be. The particulars of purpose and mechanism of action matter, which is why a blowtorch is sometimes a wrench but only if you're kind of desperate. It is always a very scandalous thing to speak ill of someone's best new electric banana-phone / dishwasher-piano that they want to sell you. But that just sounds messy to me, I'm not sure it will improve the sound quality or taste of anything involved.
> You've conflated them because they are both capable of doing work.
No, you've misunderstood the point. I'm not sure if you read the rest of the comment or got there and immediately replied, but perhaps I wasn't clear enough.
That point was not about whether it's just nice to have people around that have wide ranges of experiences, but that on a practical level having broader knowledge can help. A very sheltered upbringing means you're more likely to miss a lot of the things on the "things programmers believe about names" for example.
> And I don't look at a carpenter and wonder if his head is hard enough to drive nails like a hammer either
Your analogies are cute but seem like you're simply trying to mock rather than understand and contribute to what I think is an interesting discussion. Assuming this is in good faith:
A carpenter that has kids is more likely to appreciate the value of a shelf deep enough for larger picture books when discussing a bespoke unit for you. One that robotically cuts wood exactly where you say will require total supervision. At some level there why don't I just cut the wood myself? The value of bringing someone in probably wasn't just because I'm physically incapable of using a saw. Depending on what I'm after I want to hand over more or fewer decisions.
Before you get stuck on that specific analogy, there's a really crucial point that I want to highlight from my other comment
*At some level unless all you want is "loop over the array and sum the results into a variable called sales_total" converted into code, you have to have some broader knowledge about things.*
Llm labelling is so incredibly useful, as is transforming labelled data to other valid but different forms (like where you might train on sentences but also randomly replace days of the week with others).
You can also do stuff like setup active learning but have the labeller be an llm as well to make things more efficient.
Definitely worth it for PoC level things if not full ones.
Edit - also reviewing, so it can run training, test, review failure cases and investigate itself. You can leave them to plough through a few iterations where the early part is the classic time you’d have a few obviously bad sets of results.
There are absolutely good reasons to use smarter things for classification. Svm with tdf idf for example is super fast but will make very bad classifications at times in ways entirely unfixable with that system (thinking back to bats being an acronym for a theology degree classification or similar)
That depends on how long it’s sitting there, given they are two different things to manage it makes sense that you’d either have gpus sitting unused while a dc gets built or a dc sitting empty while you wait for gpus.
Just because a system is end-to-end encrypted doesn't mean the users are anonymous. If someone reported to me a download link with decryption key for my file service, I can probably find the IP address of the person that uploaded it. Then pass it off to whatever govt entity that deals with that.
That is not what they say. There are errors in the data, the data does not have the real name it has “female child” in instead.
Perhaps there’s something else in the post that you’re talking about but please do take the time to actually read what’s there, I’m only telling you what’s written in the text around the problem you think you’ve found.
It mentions that it may rely on other services or security measures running- I wonder if there’s something like this hitting a firewall or av and then that calling out to paint to check file type or size out something like that?
Coding an exercise app will benefit from a model that can code and understands what exercise is. A car showroom website will benefit from a model that understands what relevant filters would be.
reply