Except when doing personal projects for fun! Indeed, this is imho the number one reason (tied with a couple of others e.g. mental health) to do personal coding projects in the first place: it is a safe space to give those shiny new tech toys a go and see how they really perform (sometimes it is: very well! In those cases you know you can then use them for business).
The title is deliberately provocative but if I'm reading this article right it seems to push an argument that I've made for ages in the context of my own business, and which I think - as the article itself suggests - actually represents the best practice from before the age of ChatGPT, to wit: have lots of ML models, each of which does some very specific thing well, and wire them up, wherever it makes sense to do so, piping the results from one into the input of another. The article is a fan of doing this with language models specifically - and, of course, in natural language-heavy contexts these ML models will most or all be language models - but the same basic premise applies to ML more generally and, as far as I am aware, this is how it used to be done in commercial applications before everyone started blindly trying to make ChatGPT do everything.
I recently discovered BERTopic, a Python library that bundles a five-step pipeline of now pretty old (relatively) NLP approaches in a way that is very similar to how we were already doing it, now wrapped in a nice handy one-liner. I think it's a great exemplar of the approach that will probably emerge from the hype storm on top.
(Disclaimer: I am not an AI expert and will defer to real data/stats nerds on this.)
As someone with a Philosophy BA and a keen but very amateur interest in copyright law, this development fascinates me and I desperately want to understand it. Can anyone give me an example of where this fallacy would lead to unfairly issuing or failing to issue a patent?
I write fiction sometimes and I've got this story I've been working on which has languished by the wayside for at least a year. Whacked it into the podcast machine. Boom. Hearing these two people just get REALLY INTO this unfinished story, engaging with the themes, with the characters, it's great, it makes me want to keep writing.
These videos were super fun to make and kept me sane when I found myself with far too much free time and a bunch of world news to avoid. I never did the fifth (and final) walk but it's only about 100 meters long so I hope one day to do it in person (if I ever end up with that much free time again).
Big fan of this write up as it presents a really easy to understand and at the same time brutally honest example of a domain in which a) you would expect LLMs to perform very well, b) they don't and c) the solution is to make the use of ML more targeted, a complement to human reasoning rather than a replacement for it.
Over and over again we see businesses sinking money into "AI" where they are effectively doing a) and then calling it a day, blithely expecting profit to roll in. The day cannot come too soon when these businesses all lose their money and the hype finally dies - and we can go back to using ML the way this write up does (ie the way it is meant to be used). Let's hope no critical systems (eg healthcare or law enforcement) make the same mistake businesses are before that time.
On the flip side I thought the write up was weak on details and while "brutally honest" it did not touch on how they even tried to implement an LLM in the workflow and for all we know they were using an outdated model or a bad implementation. Your bias seems to follow it though, you have jumped so quickly into a camp that its easy to enjoy an article that supports your worldview.
To be honest, I exited the article thinking the answer is "no", or at least, perilously close to "no". The same amount of work put into a conventional solution probably would have been better. That cross-product "solution" is a generalized fix for data generation from a weak data source and as near as I can tell is what is actually doing most of the lifting, not the LLM.
That said, I'm not convinced there isn't something to the idea, I just don't know that that is the correct use of LLMs. I find myself wondering if from-scratch training, of a much, much smaller model trained on the original data, using LLM technology but not using one of the current monsters, might not work better. I also wonder if this might be a case where prompt engineering isn't the way to go but directly sampling the resulting model might be a better way to go. Or maybe start with GPT-2 and ask it for lists of things; in a weird sort of way, GPT-2's "spaciness" and inaccuracy is sort of advantageous for this. Asking "give me a list of names" and getting "Johongle X. Boodlesmith" would be disastrous from a modern model, but for this task is actually a win. (And I wouldn't ask GPT-2 to try to format the data, I'd probably go for just getting a list of nicely randomized-but-plausible data, and solve all the issues like "tying the references together" conventionally.)
How so? Their implementation was interesting but I think it missed the whole setup on what did and did not work on the LLM side. Have just a few of those details would have made it very interesting. As it stands its really hard to decide if LLM is or is not the way.
If you have such an opinion why not share how I could communicate it better?
Your line about the parent commenter's bias was weird and rude. You've never met the person and are accusing them of something you're in the process of doing yourself.
Your comment is perfectly fine - obviously. You even used 'seems'. You even even saved me from wasting my time reading another bullshit article about LLMs from someone who can't be bothered to learn anything about them. Thanks!
"If it didn't work you didn't believe hard enough" also known as "Real Communism has never been tried" or "Conservatism never fails, it can only be failed" is a sort of... information-free stock position.
Basically, if thing is good it needs to still be good when tried in the real world by flawed humans, so if someone says "I tried thing and it didn't work" replying with "well maybe thing is good but you suck" isn't productive.
Sorry I think it’s totally justified to question an article when they provided nothing more beyond we tried and it did not work. The whole premise was can it be done but it was missing basic information to draw a conclusion.
Now maybe I was too weird in my response to the OP but it really went into a LLMs are bad narrative.
"Concrete blows most other materials out of the water."
In fact, according to Wikipedia, concrete is the "second-most-used substance in the world after water" - I was on the Concrete Wikipedia article while I read this as I realised it was a thing I have never thought about despite its ubiquity. Amazing how that can happen.
Always nice to see my Alma Mater in the (Hacker) news. Monash always seems like a bit of a non-entity compared to the big sandstones and ANU but they are always doing newsworthy stuff.
I also use make this way and have done for years. I even have the same kind of religious ritual the author has, like writing the Makefile is part of setting up the codebase and organising in my own head how the whole local dev environment is going to work.
The only thing is, this isn't what make is actually for. A number of commenters have recommended Just - the one I've been using on my personal projects is Task - https://taskfile.dev/ - which is pretty great. As other commenters have said, the problem is that make is installed everywhere already. I would love to see a task runner become standard to the same extent, and will have a look at Just if that's the one people are using.
