senseamidmadness comments on GitHub - Gathin23/cleanyourtv: Debloat any Android or Google TV over Wi-Fi and get an Apple TV-style home.

[–] senseamidmadness@lemmygrad.ml 0 points 4 days ago (9 children)

I know enough to know that these mainstream Silicon Valley models give inconsistent results, per the people I know in the industry, and in the hands of inexperienced developers they write some seriously opaque spaghetti. They are also "breaking out" of constraints regularly if the rumors are true.

I also know directly that LLM-generated Internet slop has made my life and my job more difficult. Accurate information on the Internet now takes me double or triple the time to find than it took before 2023 because of an abundance of ChatGPT-generated websites that are nothing of substance and festooned with ad banners, but the search bots point at them preferentially. Search results simply aren't trustworthy like they used to be.

So why should I give one of these Big Tech models access to my hardware? How can I be assured it's safe other than the already-worthless word of OpenAI, Anthropic, etc?

permalink

fedilink

source

parent

hideshow 9 child comments

[–] yogthos@lemmygrad.ml [S] 4 points 4 days ago (8 children)

What you don't seem to realize is that humans also give inconsistent results. The way we deal with that is by having specifications, tests, code reviews and so on. People who don't work with LLMs seem to have this naive idea that it's sort of like a slot machine where you put a query in and then you either get a correct result or some nonsense and you have to try again.

The way this process actually works is that you start by understanding the problem and figuring out how you want to solve it in terms of architecture, data structures, and algorithms that will be used. Then you get the LLM to come up with a rough shape of the solution, and iterate on it until it works the way you want.

I have no idea what the marketing hype you're quoting about models 'breaking out' or how much time it takes you to find things online has to do with anything either. We're talking about a specific use case for LLMs in the context of agentic coding here.

I also have no idea why you have to give anything to some big tech companies. Evidently you're not aware of the fact that there are plenty of open Chinese alternatives you can use, and that it's possible to run local models now as well. Nobody is asking you to give anything to OpenAI or Anthropic.

It's pretty clear that you've spent absolutely no time actually trying to understand the subject and you have a reactionary position as a result.

permalink

fedilink

source

parent

hideshow 8 child comments

[–] senseamidmadness@lemmygrad.ml 0 points 3 days ago* (last edited 3 days ago) (7 children)

did you not read the Github link you posted? It specifically says the Anthropic's Claude was used in the TV "debloat" process and calls out Claude and Gemini as the options for repeating it

sure, if you're using locally hosted open-source models it avoids all the horrors of Silicon Valley and I've been told it's a useful tool, but I have yet to see anybody explain quantifiably and repeatably where a coding LLM actually saves time or effort in novel ways with trustworthy results. the software engineers I know say they spend as much time editing and proofing the LLM output as was "saved" by using it, and initial scientific surveys on its professional use say the same thing

I am open to being proven wrong but I am justified in not trusting technology that is being pushed by capitalist monsters who openly state they want to use it to eliminate jobs, especially creative human ones

permalink

fedilink

source

parent

hideshow 7 child comments

[–] yogthos@lemmygrad.ml [S] 5 points 3 days ago (6 children)

Yup, I did read it. The fact that the person used Claude to do it doesn't mean you have to use it yourself. In fact, the best thing you can do is to use open models because it directly cuts into the business of companies like Anthropic. They're not worried about a boycott of their tech because they know there's an insane amount of money being poured into them. What they are afraid of, as they openly admit, are open models.

Meanwhile, you're literally talking to a software engineer who works with these tools every day. I can tell you from direct experience that they very much do work. The scientific surveys you refer to used laughably small samples, and the technology has only gotten better since.

Again, nobody is asking you to use technology pushed by any capitalist monsters here. It's also really weird to see people complain about automation on a Marxist forum of all places. Everybody knows that automation is used against the workers under capitalism, that's not a reason to reject automation.

permalink

fedilink

source

parent

hideshow 6 child comments

[–] senseamidmadness@lemmygrad.ml 0 points 3 days ago (5 children)

Okay, but can you please explain how it helps you instead of just saying it does?

permalink

fedilink

source

parent

hideshow 5 child comments

[–] yogthos@lemmygrad.ml [S] 5 points 3 days ago (4 children)

Sure, it automates writing a ton of repetitive code that you'd have to write by hand otherwise. Most programming tasks aren't novel or interesting in any way. In most apps you have to do things like render UI with stuff like buttons on them, wire it up to a service, create HTTP endpoints, talk to a database, and so on. These are well known and repetitive tasks that have to be done in every application. There is nothing challenging or interesting about them. Once you've done this stuff enough times, it gets extremely tedious to do. And you have to do all this stuff before you can get to anything that's actually interesting or novel in any given application. LLMs do a very good job automating a lot of this repetitive code allowing you to work on the parts of the app that you actually care about.

permalink

fedilink

source

parent

hideshow 4 child comments

[–] senseamidmadness@lemmygrad.ml 1 point 2 days ago* (3 children)

Thank you very much. I really had not seen a full explanation anywhere before from someone who's gotten genuine benefits from it, because as you know there are piles of viral marketing everywhere extolling the big-name models for things they are not (like automatic hackers, real human personalities, etc)

One senior engineer I know very well who works for a Big Corporate Retail company told me they had a ChatGPT subscription thrust on the entire software department, and he removeded about it quite a lot. Another I know works in a company that makes medical software and he said they bought everybody a Claude subscription and demanded they use it. He is not a fan and had the experience I mentioned above, having to proofread through every bit of output and constantly correct it. To the point that its raw output would not even pass the compiler without erroring out most of the time.

What models have you been using, and what have you been feeding them as training data?

permalink

fedilink

source

parent

hideshow 3 child comments

[–] yogthos@lemmygrad.ml [S] 5 points 2 days ago (2 children)

Right, there is a lot of insanity going on with this tech right now, and companies are doing nonsensical things with it. But the mania has to be separated from what the tech can actually do, and whether it's useful or not. Eventually the bubble will pop and a lot of this nonsense will go away with it. So, I'm not really worrying too much over that aspect.

In a way, I'm also lucky that it's not being pushed on me at work, and I can decide when and how to use it. Which makes a big difference of itself. I can very much understand how people who are mandate to use LLMs for everything and are then have their timelines for projects adjusted based on that would be very frustrated.

I've been mostly using DeepSeek and GLM, and my personal projects are open source, so I'm not to worried about the models getting fed my data.

permalink

fedilink

source

parent

hideshow 2 child comments

[–] senseamidmadness@lemmygrad.ml 3 points 2 days ago (1 child)

Chinese open-source models which keep undercutting the American techno-fascists by performing better and more efficiently for free? Awesome. I'm fine with those.

I probably hear so little about their real-world use cases because none of the American press want to upset their capitalist masters, and there's not a ton of info on my usual Lemmy instances either.

permalink

fedilink

source

parent

hideshow 1 child comment

[–] yogthos@lemmygrad.ml [S] 3 points 2 days ago

Yeah, western media isn't a great source on this tech for the most part. And Lemmy tends to mostly attract liberal left which predictably attracted a reactionary position blaming LLMs instead of the underlying capitalist relations. I find Cory Doctorow has been doing a fairly good job covering this in a sober way.

permalink

fedilink

source

parent