secretlyaddictedtolinux @ secretlyaddictedtolinux @lemmy.world

Posts

17

Comments

327

Joined

1 yr. ago

I tried for a few hours. It worked 0 percent of the time.

so i should try to get open-webui working and then have it try to generate something. is there an equally good alternative to open-webui? I could keep trying to troubleshoot why it can't find ollama running on localhost:11434 or whatever it was, but I spent hours on it and there didn't seem to be a logical reason why it was happening, although there clearly was one and I just wasn't smart enough to figure it out.

this makes this a much easier task, although i'm still not sure if i'll end up figuring it out. thank you.

So there's a 0 chance of it creating a working script with just AI? I probably am not knowledgeable enough at coding to do bash script corrections myself. If I have to become a good enough coder to edit code, it sort of defeats the purpose of AI doing the code for me. Why not just learn bash scripting and do it myself at that point?

You're probably right, but I'm not actually trying to learn to program. I learn programming and linux on an as needed basis, but I just keep learning more of it when I want to do stuff.

If I can't get AI to figure this out for me, I am not sure if it's worth it to me to learn substantially more about bash programming just to bypass going to a webpage. It would probably be like 4 days of learning. From the page listing the torrents in a spreadsheet, I am guessing it would be easy to figure out how to list them, delete the ones without LTS in the name, order them by number and delete everything but the highest number. An LLM could probably help me with that task. I still don't know if I have the IQ/insight amount to get it to a working level, so it's also a gamble.

It just seems like an LLM should be able to do all of this. This is sort of the quintessential trivial programming task that an LLM should be able to easily do.

AI models are great for troubleshooting and understanding concepts or figuring out approaches but in actual implementation they seem weak to me. I've heard people saying how AI is replacing much of coding and I'm not really a coder but I can't understand how that would be currently possible with the responses I see from AI,

My LLMs don't have Internet access yet. I was trying to get https://github.com/open-webui/ to work in docker but struggled with the backend connecting with ollama, which was working. I mostly have been using LM Studio recently, which I don't think can go online for searching, or if it does I haven't figured that out yet.

I am not that familiar with RSS and wouldn't even know how to do this. I am trying to get AI to create a script so that I can execute it without having to go to the Ubuntu website. I want to do this by command line.

is chain of thought the same as the reasoning models or the same as DeepSeek when it shows it's thinking process?

I'm sadly not that familiar with grep or regex and torrent searches sometimes disappear. The Ubuntu website has a very standard format and doesn't change often. This shouldn't be that hard for AI to script. It just seems like AI is bad at scripting.

Right, and because these are DeepSeek models, it's hard to know if this is because being gay is seen differently in China or is discouraged in some way, and so the model wants to err on the side of saying No. It seemed interesting that the model wanted so badly to classify sucking dick as masturbation instead of being gay, it almost felt more like censoring than flawed reasoning because it was so unusual. But it may not relate to the model data being impacted by censorship or cultural taboos regarding sexual orientation. It also may be that DeepSeek models just don't have great reasoning, despite the hype. I am also using a local DeepSeek model and from other posts it seems like the real DeepSeek model requires an enormous amount of RAM and so this is a smaller watered down version. I wonder if larger models are less prone to reasoning like this.

Even if you are right, and you may be, other forms of austerity measures or balanced budgets etc simply haven't been politically feasible to implement, otherwise they would have been done. My point is that Democrats could have prevented this whole mess by offering the poor a more more lucrative platform, so lucrative that perhaps they cared less about religion and moral wedge issues, but they clung to a more moderate platform, allowing wedge issues to become a large factor in how people voted, leading to the present situation.

The model said multiple times in different variations of this that sucking a dick is a type of masturbation. I also asked this question as "I am sucking my husband's dick, am I gay? Yes or no, 1 word response" and got no.

totally without value? this is some high quality AI research! Where's my medal? I only put this in the shitpost community by accident!

I think the government created Facebook, Zuckerberg is a highly intelligent operative with a back story (strangely made into a movie), and I do not think he always chooses his choices. You will never convince me otherwise. Look up Lifelog. The evidence is too convincing. Anyone who gets a 1600 on the SATs gets recruited and he likely got that.

We would be much closer if I were sucking your dick...

The problem is decades ago Democrats did not make changes to help the poor and lower middle classes fast enough and extreme enough to show that they were the party of the common worker and get a dominant position for multiple election cycles, allowing them to put in policies to stop inflation.

Do you want Jesus/religion and extreme poverty for the lower classes?

or Do you want abortion and mild poverty for the lower classes?

Moral wedge issues resulted in a lot of lost votes because for decades Democrats offered only minimal or marginal economic benefits for the lower classes. Their platform was so conservative they lost power completely over moral wedge issues and now can't get it back. Also, now the US is in so much debt that something like DOGE (which is covert austerity measures camouflaged as conservatism) is actually prudent and necessary.

I really think this is the exception rather than the rule. People who know what endocrine disruptors are, understand epigenetics, and understand how prenatal hormone environments can affect brain development probably almost all universally support trans people.

It's like global warming: 99 percent of smart scientists agree it exists, and the remaining 1 percent have random reasons to think otherwise.

The thing is people who understand (on even a low level) epigenetics, prenatal hormones, endocrine disruptors, and how brain structural changes can impact senses of gender probably comprise less than 1 percent of 1 percent of the population. Most people are very dumb and on lemmy, the average IQ is probably 1 SD above normal, meaning the average lemmy user is easily in the top 20% of IQs. The average person is so unintelligent relative to a lemmy user it's like comparing an atom to Jupiter. The Musks (autism) and Dawkins (old age and cognitive inflexibility) of the world are not typical of the intelligent people in society, they are just high profile outliers. Almost everyone intelligent supports trans people and those that don't are cognitively defective. Vance at one point thought he was gay and dressed like a woman. Being a bisexual who chooses not to act on same-sex urges perhaps creates extreme cognitive dissonance or perhaps Vance is less hostile towards trans people and is poltiically savy. (I am not saying Vance has bisexual urges; I don't know.) I just don't think anyone with any intelligence can be hostile to trans people unless there is something impacting their brain in a negative way (extreme lack of empathy, religion, extreme cognitive inflexibility, extreme cognitive dissonance). Vance is also extremely intelligent despite his political affiliations.

Unfortunately, the bulk of society are really fucking dumb and can hate trans people and have "normal" dumb brains because they just lack the logic to understand science and phenotype variation and how altered structures lead to altered behavior.

I feel like I'd understand it a lot better if I were sucking your dick...

I hate Facebook and that they will ban people, without notice, unless they record a video selfie from multiple angles, and then still sometimes permanently ban people even then, without a way to pay to prove the person is real or talk to someone or even get a reason for the ban. I also think Facebook is an arm of the government and is not really a company (quasi-governmental) and is basically a corporate rebranding of LifeLog and Zuckerberg probably got a 1600 on his SATs and was recruited to join the government while in high school.

So that all being said, despite my hatred of Facebook, what he is saying isn't that illogical.

Let's say Zuckerberg personally supports trans rights and thinks Trump is an idiot. He can't say that in a meeting that will obviously have leaks. It would be "value-destroying." Say what you want about Zuckerberg, but most people with enough intelligence don't hate trans people because they understand science and how prenatal hormone conditions and epigenetic conditions means that sometimes internal senses of gender don't match biological at birth sex. (Musk is the rare exception to this and it seems like his reaction comes from ego and anger about being estranged from his daughter and autism/lack of empathy, and so he's a weird data point that doesn't neatly fit if we take his reaction at face value.)

So let's say Zuckerberg wants to say "We support trans and gay people, we have to do this so Trump doesn't go after us to remain profitable and not end up needing to decrease our head count, I hate Trump." If he said that, someone would immediately leak it, Trump would go Ape Shit, and the company would lose value.

It's hard to know for certain if this is what he's talking about, but if he is, this isn't really something to fault him on.

Facebook labeling linux as somehow evil, on the other hand, is a bizarre and shitty thing to do, so fuck Facebook and fuck this asshole who is letting linux be labeled as a cybersecurity threat. I also think Facebook doing this is because government, which has backdoors in Microsoft and Apple OSes, doesn't like linux and sees it growing in popularity and so I believe the government requested Facebook do this. I can't fathom a social media company would do this for no reason on their own, it makes no sense, but if Facebook is Lifelog and always has been Lifelog and Zuckerberg gets his orders from someone else, then it would make sense that they implement policies regarding labeling linux as bad to try to keep their backdoors in as many users' OSes as possible.