But that's not something you'd use an LLM for. There have been computer vision systems sorting bad peas for more than a decade[0], of course there are plenty of use cases for very fast inspection systems. But when would you use an LLM for anything like that?
Nobody said you would use an LLM for that. It's an example of a process where "industrial inspection, in particular, [would] benefit from lower latency in exchange for accuracy".
The point of their comment isn't that you would use an LLM to sort fruit. It was just an illustrative example.
The discussion was about fine-tuned Qwen models, not industrial inspection in general. I would also find it interesting to learn about what kind of edge AI industrial inspection task you could do with fine-tuned llms, not some handwavy answer about how sometimes latency is important in real time systems. Of course it is, so generally you don't use models with several billion parameters unless you need to.
> No, we are literally trying to find a use case where using a lower accuracy LLM makes sense for a vision task.
They're reconfigurable on the fly with little technical expertise and without training data, that's really useful. Personally in projects for people I've found models have fewer unusual edge cases than traditional models, are less sensitive to minor changes in input and are easier to debug by asking them what they can see.
Seems like a way to use a sledgehammer to hammer in screws, and inviting nondeterminism in important systems. Besides being way larger and more complex than what most specialized industrial processes need, they are also vulnerable to adversarial attacks.
> Seems like a way to use a sledgehammer to hammer in screws
The lazy analogy the other way is that developing a custom system to do these jobs is like hiring a team of experts to spend 2 years designing the perfect crosshead screwdriver that fits exactly one screw (and doesn't work if the screw starts slightly rotated) when you have a flathead one right next to you that'll work and it'll work right now.
> and inviting nondeterminism in important systems.
Traditional ML is just as non-deterministic.
> they are also vulnerable to adversarial attacks.
Typically not relevant in these kinds of cases but also this is easily a problem in many traditional ML algos.
A flathead screwdriver is not a valid analogy, because LLMs are big complicated and opaque machines. And while other ML methods are non-deterministic as well, gaussian process, decision trees or even CNNs are easier to try to make sense of than these huge black boxes.
And I still haven't seen a single example of anyone actually using a finetuned Qwen in industrial inspection, which leads me to believe than nobody is actually using it for that, but some people want to use it because it's their new favorite toy. You don't need a VLM to count cells in microscopy images, or find scratches in painted parts, or estimate output from a log in a saw mill. I can see the use case for things like describing a scene from a surveillance camera, finding a car of a certain model and colour, or other tasks that demand more reasoning or description. But in those cases latency is not super important compared to getting the right output, which was the tradeoff discussed from the start of this thread.
The last thing I'd want to deal with is to have a computer say something like "You're absolutely right, it was wrong of me to classify the metal debris as food".
I’ve used multimodal LLMs for this sort of task and if a fine tuned model would get reasonable performance compared to frontier models I’d use that. Running things purely locally lets you massively simplify the overall architecture and data transfer requirements of some of these tasks if nothing else and lower latency means you can report problems much faster (vs transfer images off device, batch process).
> The last thing I'd want to deal with is to have a computer say something like "You're absolutely right, it was wrong of me to classify the metal debris as food".
The cnn will do that potentially more often and it can be because it’s just not seen enough examples of the debris at that angle or something else equally irrelevant to a human.
They worked best when everybody were farmers and had to get up early and go to bed early. Now most people don't live their lives centered around noon, our free time comes after our work is done at around 17:00, so having more light in the evening instead of worthless light in the night makes sense.
Farmers have to wake up early because their animals wake up at sunrise and some tasks are best performed at that time. So they wake up before sunrise regardless of the clock time.
Human, like farm animals, are better off if they wake up at sunrise and go to sleep in full dark. At the equator that's easy, wake at 6, bed at 10PM. And standard work hours are 7-3 or 8-4.
So, it sounds like you're actually arguing that the numbers are just a construct and that we should all just use UTC and set appropriate work hours to the times that most correlate to the solar day in our region rather than adjust the clock approximately 1 hour per 15 degrees around the equator and have an International Date Line.
I think this would make way more sense, when they say the Olympic Opening Ceremony start at 18:00, its 18:00 for everyone around the world. No one as to work out which TZ Italy is in or scheduling meetings with Tech Support in far flung locales does not require knowing IST is how far ahead or behind.
> He promoted worldwide standard time zones, a prime meridian, and use of the 24-hour clock as key elements to communicating the accurate time, all of which influenced the creation of Coordinated Universal Time.
The one bit where this would be problematic would be "what day is it?" When does today become tomorrow?
There are a lot of systems that we've built that depend on that distinction. Things like business days and running end of day so that everything that happens on March 2nd is logged as March 2nd. I've encountered fun with Black Friday sales where the store is open over the midnight boundary and the backend system really wants today to be today rather than yesterday (sometimes this has involved unplugging a register from the network so that it doesn't run end of day, running EOD on the store systems, and then plugging the register back in after it completes and then running a reconciliation.).
Other than that particular mess of banks and businesses... yea, running everything on UTC would be something nice in today's world.
Aside on the "changing clocks" and realizing my flexible schedule privilege at a company I worked at I switched my schedule from 8-4 to 9-5 with the change in daylight savings so that I maintained a consistent "this is the hour I wake up".
When people propose switching to UTC what they are actually proposing is that everyone nominally switches to UTC but still uses local time informally in everyday life, which is a worse system than time zones. At least with time zones there is a way to know what time it is in any given place. With informal time you lose that.
No. that does not follow. Abstraction is useful. Having commonly understood terms (in this case hours of the day) that share certain traits regardless of where you happen to be in the world facilitates communication.
Right, but where I live sunrise is in the middle of the night in the summer (around 03:30). Using standard time in the summer gives me one less hour of useful sunlight in the evening, and while it doesn't technically disappear it gets moved to where I can't use it because that's when I sleep. It's the same for people further south as well, another bright hour in the early morning before they wake up is a wasted bright hour that would make more sense in the evening, when most modern humans are awake. The argument "noon should coincide with solar noon" is nonsensical to me, the clock is a social construct and should make sense for how most of us live our lives.
But the social construct of work hours shifted later by more than that one hour during the last century, so this is not what people actually prefer by their actions.
People disagree on whether to prioritize mornings or afternoons in the winter. For the summer, only very few people care if the sun rises at four or five (or whatever), but most people like having long summer evenings. Therefore the summer tips the scales.
Then they are also social activities that you just need to wait for in summer, because they can only happen after sunset. Viewing a movie (outside), sitting around a fire, having a party all just really happen after sunset.
The maintainer has used a hyped language to write a simple editor that already exists. Do I need to say more?
OK.
The code will be abandoned in 2 years. Maybe it doesn't comes to more features.
Oh god no, it's not the maintainer. It's frankly a student with no prior experience in both the language and the codebase, asking the maintainer permission for pushing a lot of ai generated code with chatgpt for his resume?
Atleast he has the decency to ask for stuff first and being straight.
The maintainer is the first comment, agreeing with the post author:
> I concur, but there are two issues with this: Building the foundation of an editor is way harder than building features later on top of that, and currently it is unlikely that Microsoft will fund me to spend half a year working purely on this project. So, I'll work on this whenever I can, which is not much.
The drywall wall is stronger, heavier thicker stuff and sometimes doubled up. We also often use steel work as the studs (particularly good professionals) as it’s stronger and faster than wood to put up. Then all the wiring is in conduits, and it’s acceptable to put water feeds on the outside of walls in the room for servicing. Then it comes to our bathrooms which are proper wet rooms and usually built to a very high standard to meet insurance needs.
I watch a lot of building videos from the US, it’s eyeopening watching for someone used to better construction methods.
The construction of UK inner walls is even better, it”s often plaster applied on plasterboard/drywall usually by skilled trades. Very strong.
Running conduit for electrical wiring in a house is a huge waste of labor and material. PVC insulation and a nylon jacket is just fine for 2.5mm^2 (#14AWG) conductors, which is what 90% of the wiring in a house will be.
The only place that conduit is mandatory in residences in the US is Chicago.
Hell, most office buildouts in the US use very minimal amounts of conduit, most of the lightning and receptacle branch circuits are metal-clad cable (MC cable).
If your main gripe about the Rust GUI ecosystem is that it's not mature then rewinding 20 years and using Qt/WPF/etc sounds like an excellent alternative. Old and mature versus modern and immature.
> I also live in Europe and tip, specially if I know that the salary of the staff heavily depends on tips.
> If I ever find the system too unfair for the workers, then I won’t go to those restaurants anymore.
Sounds like you only tip once at each restaurant then? Not paying a reasonable salary to employees and assuming they'll beg customers for extra money to make up the difference seems unfair to me.
I can't say if it's unfair or not. I would prefer every worker to get a decent salary, but no idea how they feel in countries where tipping is widespread like the US.
But, if I go to a restaurant in the US, or, Argentina (where tipping is also a thing), then I'll tip, and consider the price of the food to be 10, 15 or 20% more expensive. Otherwise, I won't go, because then I am complicit with the exploitation of the workers.
Incorrect, the reason they don't get a full salary is because tipping is allowed.
If you don't tip, the worker does not magically get a salary. How would they? No, they actually make less money.
This whole "well if you think about not tipping is actually giving them more money" thing is the purest and most refined form of cope I've ever seen. It obviously doesn't work like that. Maybe if everyone did it. But you just doing it does nothing.
You're 100% allowed to not tip. What you're NOT allowed to do is not tip and then somehow try to claim you're helping the worker. You're not. Like, objectively, you're not. That's just literally not true.
Maybe you can log all the traffic to and from the proprietary models and fine tune a local model each weekend? It's probably against their terms of service, but it's not like they care where their training data comes from anyway.
Local models are relatively small, it seems wasteful to try and keep them as generalists. Fine tuning on your specific coding should make for better use of their limited parameter count.
[0] https://www.youtube.com/watch?v=eLDxXPziztw
reply