Trust me, it’s not.

That’s a silly thing to say. Like I said, I could read something like that from time to time so you’re asking me to trust you over my own experience. People also post/publish fiction of varying quality all over the internet, and it gets read. I’ve seen worse writing than that with hundreds or thousands of reads.

Maybe you’re only talking about a publisher buying the work and publishing it but you never said anything like that. Even so, I’ve seen some books that were pretty bad so I’m not sure I’d trust you even there.

Very sorry to contradict you, but this is absolute shit.

To be clear, I’m talking in relative terms. Would you argue that ChatGPT did a massively better job and didn’t write “absolute shit”?

It looks good on the surface, but that’s all.

From some of the stuff I’ve seen published, that might just be enough for certain people. I could even be that “certain people” from time to time, sometimes just the right theme, setting and some time to fill is sufficient.

I’ve hit my limit for dealing with bad faith argument.

Haha. That’s rich coming from someone that has yet to actually address the substance of my position. Literally the only thing you’ve done so far is dissemble and use bad faith tactics like the straw man fallacy. While it’s possible I’m wrong/misguided I’ve stated what I believe and explained why I believe it. Discussion isn’t possible when the other party never engages though.

I’m not sure why you’d be posturing deep in a comment thread like this, but for your own sake I actually hope that’s what you’re doing. Otherwise this is a super yikes level of self delusion and eventually you’re going to run into the hard wall of reality and it’s not going to feel very good. These tactics don’t work against people that have a clue.

65B LLaMA models can actually do a pretty good job of writing. Here’s two examples with Guanaco 65B (bold part is my prompt):

tags: fairy tale, animals, dog, wolf, fox, death, humor, dark storyline, violence, loss

Animals in a forest setting investigate a series of gruesome murders that recently occured. Written in the style of classics like Animal Farm and Watership Down, the writing is vivid and very descriptive. The dialog is thoughtful and often quite witty. It’s clear the author really understands animal behavior and has done their research well!

—

Chapter 1: An Unfortunate Discovery

A fox by species, a detective by trade, you’ll only have reason to know my name if the worst has come to pass. It’s nearly winter and a bitter wind drives stinging sleet into my face, but it’s still not as chilling as the scene before me now…

I was summoned here by an urgent message from a panicked hedgehog. She told me she found her friend lying dead on his doorstep with his throat ripped out - black fur matted with blood. I rushed over immediately and saw for myself what had happened. He looked so peaceful despite being cut down in his prime - a young wolf just starting doing well for himself - taken too soon. His home nearby showed no signs of struggle or forced entry. Whoever did this must have caught him off guard somehow. I didn’t hear any howling either. That would have been easy enough to miss though since he lived alone deep in these woods where few creatures tread. I made sure to secure the crime scene and look around carefully without disturbing anything more than necessary until other investigators arrived. They should be here soon. We can’t afford to lose evidence in cases like this. Times are already hard enough as it is…

As I waited and pondered who might have committed such a horrible act, something felt wrong about all this. Surely a predator like me could smell another predator’s scent? But there were none that stood out among the melange of odors lingering here. How strange…

Soon after, several others joined me including some friends of mine. A stoic bear named Growler, grumpy badger called Grumpus, and a kindly old raccoon who goes by “Doc” due to his extensive knowledge of medicinal plants and wildlife biology. Together we began our investigation proper by gathering clues and questioning nearby witnesses while trying to minimize contamination through contact with them (we took care to put up caution tape first). Unfortunately, they hadn’t seen much useful apart from occasional glimpses of movement deeper in the undergrowth. Still, we decided to check those areas next along with searching the surrounding woodlands thoroughly for any additional victims. And find one we did, although sadly she suffered the same fate as poor George. Another young wolf lay beside a stream, body cold and stiffening. Someone snapped her neck cleanly like a twig. This couldn’t be coincidence surely? Not two deaths in quick succession like this.

<prompt> before me or what I must relay when I return home. My mind races with questions as I survey this brutal crime scene; who could do such a thing? Why was no one there to stop them? And how many more victims lie undiscovered further out in these woods? A lone paw print leads away from where a rabbit family once happily resided, now reduced to bloody scraps scattered among splintered twigs and torn fur. This isn’t just some random predator attack, something far more sinister is at play here…

I turn back toward town, determined to find answers. As I trudge through the snow, each step feels heavier than the last. How will I break the news to those closest to them? What words can possibly bring comfort after so much senseless suffering? I shake my head, trying to focus on the task at hand. There are others depending on me right now, they need someone strong and steady to guide them through this darkness. I won’t let them down.

The first person I see upon entering town is old man Badger, his white whiskers blown about by the gusting wind. He looks up at me expectantly, “Well Fox, did you find anything?” His voice quavers slightly, betraying his concern for the missing families.

“I’m afraid I have bad news,” I say somberly, “there were signs of a struggle near the burrow entrance, but no survivors.”

Badger sighs heavily, “Dear me, this is worse than we feared. We must alert the council immediately!”

We hurry over to the meeting hall, a large hollow tree that serves as our central gathering place. Inside, several other animals are already waiting anxiously for word of their loved ones. They look up hopefully as we enter, then quickly realize the grim tidings we bear. A collective groan fills the room, followed by muffled sobs and whispered prayers.

Mayor Bear calls for order, her deep voice cutting through the din. She motions for us to join her at the front of the room, “Please tell us everything you saw, Fox. Every detail may be important.”

I was hoping to avoid getting deep enough into this that I have to break out the block quotes myself, but oh well.

Like I said, no one’s twisting your arm here.

I don’t think I’ve been any less charitable than you and weirdwallace75, though.

I can’t speak for anyone but myself but if you look at my posts and your posts, I think we can easily see this really isn’t true at all.

You made a caricature of your opponents position - they don’t like guns because “guns bad” when obviously there’s a lot more nuance than that. I challenge you to link a case where I did anything similar. Just as an example. You’ve also made a bunch of quite uncharitable assumptions with little evidence, like the “talking points” thing.

See the definition of talking points.

By the definition you linked, your accusation is just plain factually wrong. Nothing was prepared in advance, I’m (obviously) not following a script.

Also, this looks like a contradiction:

Not necessarily mindless, but certainly low-effort and static.

I didn’t say that they were easily refuted. Just as I don’t find the talking points convincing

So they’re low effort, static, you (and presumably others that agree with your position) have heard/seen them all before and yet they aren’t easily refuted? That really doesn’t make sense. I have my own pet cause and there are very common responses I’ve seen before too: as a result, I can crush them with almost no effort because I know exactly where the conversation is going.

If you’re so familiar with the subject, have seen all the arguments before but can’t muster strong counter arguments, link reputable neutral sources to support your position, etc then maybe you should reevaluate whether the ground you’re on is actually solid. Lest you be tempted to turn that line of argument around on me: don’t forget, I never claimed to be super well-informed and familiar with it.

You likened planning for fascist violence to planning for the rapture.

I likened a scenario where individual fascists are apparently wandering around randomly killing other citizens while the government/police don’t do anything to the rapture, because this pretty much implies a complete breakdown of civilization or a situation where having a gun isn’t going to help you anyway because the fascists have the might of the military on their side.

I didn’t say something like fascists gaining political power was that level of implausible. Unfortunately, it actually seems all too plausible: although the killing random lefties/liberals en masse is very improbable. Like I already said, even if you look at one of the most extreme examples in history such as Nazi Germany it still didn’t happen like that.

You’re not. I’m certain enough of it to bet money.

The point is that my position on this is completely independent of any politics. It’s like if the question was “Is the best tool for slicing bread a spoon or a knife”: would it matter if I’m politically left or right? No: there’s a fact of the matter about what tool is effective for slicing bread, there’s enough evidence to show knives are clearly more effective there and if my politics affect me accepting that and I argue the spoon side then I’m being irrational.

There are lots of subjects where politics do have an influence and philosophical points where there’s a less clear answer but here we’re talking about practical effects from taking a certain approach. Politics should have little bearing there.

I’m not really talking about utilitarianism vs egoism or whatever else,

Huh? I don’t get your response. Perhaps you’re not familiar with Utilitarianism? It’s a moral philosophy based on maximizing utility which is usually defined as maximizing pleasure and/or minimizing suffering. This is in contrast to other moral philosophies that might say something like “lying to people is wrong”, the Utilitarian would only look at it in terms of the actual effects and would have no problem accepting that lying was good if you could show that overall lying maximized utility.

So assuming the facts are on your side here, this actually makes convincing Utilitarians of stuff very easy. You just have to show taking a certain approach results in higher utility and the Utilitarian will be on your side and won’t say anything like “It’s just wrong to do that”. So if you could show me evidence that arming citizens actually results in less suffering/more happiness overall (and we can safely assume fascists taking over and roaming around slaughtering liberals/left leaning people is going to increase suffering/decrease happiness) then I’ll not only be able to accept it. I’ll be in your pro-gun camp.

I have very little patience for online debate at this stage of my life.

That’s fine, of course. Don’t debate/discuss anything you don’t feel like debating, but you shouldn’t make a straw man out of the position of people you disagree with or be uncivil.

In this context, you and weirdwallace75 come in with the talking points. Yes, talking points.

It’s not clear what exactly you’re accusing me of. Mindlessly parroting other peoples’ views?

They’re flawed, they’re patronizing, they’re uncompelling, and I’ve heard them many, many times before.

If what I said is so weak and easily refuted it’s a little strange that the best rebuttal you can come up with is “you’re wrong”.

If you had my worldview, you’d be an anarchist. As a (presumably) liberal, you’re relatively less concerned about fascist movements, and your prescription for dealing with them is going to rely (relatively) more on institutions and less on direct action.

There’s a grain of truth here, but it’s kind of beside the point and you’re making some odd assumptions. Why do you think you know what I’m concerned about?

Once again, while I don’t doubt we also have fundamental philosophical differences, the current disagreement (from my side anyway) is about practical ways to deal with the issue. From a purely practical standpoint, I don’t think individual citizens owning guns is going to be effective or worth the tradeoff to prevent the kinds of risks you mentioned. I could be far left, I could be liberal, I could be far right, I could be a centrist: none of that would have any bearing on something that comes down to the question of “is this an effective tool for the task”.

I’m not an anarchist, so guessed correctly there. It’s not because I love governments, institutions, central authority or because I’m opposed to anarchy (or any philosophy/approach that isn’t hurting others). My personal philosophy is do whatever you want as long as it’s not harming other people/animals (I’m a Utilitiarian). So I’m pro whatever method leads to the most happiness/least suffering.

Well, I hope you succeed in finding a way to do it, but again, it’s going to be hard to find tools and information to accomplish this. Since using the CPU for training is ineffective, most existing software is oriented toward GPU-based training.

You’re not wrong that if you could find the software and if you were willing to wait long enough you’d get the same results but getting to that point isn’t so easy. Also, it maybe not be an effective use of time/money: after all, if you could train your model in… I don’t know, several weeks on CPU and it takes a lot of effort to develop/find the resources or you could spent $4 to rent an A100 for two hours why take the former approach? You might spend as much just in electricity running all threads on the CPU at 100% for an extended time.

Participation in the conversation is completely voluntary so it’s completely up to you if you want to respond.

We’ve both read each others points, and found them unconvincing.

You didn’t really argue your point though. You said “You’re wrong” and “… But what if bad stuff happens?” It’s not like we had an actual debate here. Maybe you didn’t find the points I made compelling, but at least I tried to explain my reasoning for reaching that position.

but the threadiverse is small and we’re likely to encounter each other again.

Any negative perception I have toward you personally really doesn’t have anything to do with the actuall disagreement, but your approach to “discussing” it. “Because guns bad”, “don’t bother consulting your canned talking points”, etc is not a good-faith approach to debate. If you actually care about fostering good relations in a fairly small community where you may run into people again, I’d suggest reexamining your methods.

I’m guessing that our disagreement just comes down to a liberal vs leftist divide

I don’t think so. My position and what I’m arguing (although possibly incorrect) is purely based on what I see as the reality of the situation. A belief about whether guns are effective for preserving freedom against the government/fascists/whatever doesn’t have anything really to do with politics.

and possibly also American vs European.

Which one of us is supposed to be the American and which one is supposed to be the European?

Thanks but I prefer CPUs

Do whatever makes you happy, but don’t be too surprised if you find there aren’t many options available to support your preference. GPUs are just better suited for the task.

It’s kind of like saying “Thanks, but I prefer to use a colander to hold my drinking water”. If you really, really want to use a colander to hold your drinking water you’ll probably have to learn to construct colanders yourself since you won’t really find a colander-style water bottle for sale. Of course, even if you do go to that extent, in the end you’ll find all your effort produces inferior results compared to a super cheap water bottle made of some solid material.

There’s a huge difference between a country waging a foreign war and a country waging a war against its own cities and citizens.

Indeed, in that the country isn’t generally going to have the will to massacre its own citizens. So it’s not that the citizens have a gun that is staying its hand, it’s the lack of desire to just go ahead and slaughter them. Part of that is going to come from the fact that the country’s military is made up of people who have these citizens as their friends, neighbors, etc.

So having a gun isn’t helping you at all in that situation.

Insurgencies work and has been proven time and time again. See: Iraq

So these insurgents control Iraq now? They “won”?

Also, it’s not really a comparable situation: dealing with insurgents halfway across the world is harder than dealing with them in your backyard. The US was also not really trying to take over and just rule the country, they were at least half-heartedly trying to set up a government that could manage stuff. In addition, the middle east and oil is strategically important to the US but insurgents in Iraq are obviously much less of a pressing concern than insurgents in the US. Naturally the US isn’t going to invest the same level of resources and go to the same lengths to deal with those problems in Iraq compared to what it would do if that was happening in its own backyard. Finally, a lot of the insurgents were religious extremists. Even if every liberal in the US was armed, do you think we/they would really go to those lengths? I think we’re just too used to living comfortably and don’t really believe anything with that level of fanaticism to be running around with an AK waging a guerrilla war even if we had the AK.

So, all of this is wrong

“You’re wrong” does not constitute a counterargument.

The murdering happens before and during their seizure of political power.

So the scenario is fascists are just roaming around murdering liberals at a point before they seize political power? What are the police doing? If the police are looking the other way, the fascists already have political power. So what you’re talking about doesn’t seem at all realistic.

Even if we look to one of the most extreme examples in history -Nazi Germany - it still didn’t happen remotely like what you’re apparently concerned about.

I’ll go ahead and respond to your other post as well:

I’m not talking about the value proposition of having a gun for dealing with run of the mill crime.

This makes the value proposition look even worse. At least run of the mill crime has a semi-realistic chance of happening. Doing something that has negative value in normal times and only pays off if something very extreme like civilization breaking down occurs is kind of irrational.

because “guns bad”.

You’ll get further in life if you don’t make a straw man out of positions you don’t agree with. Although, admittedly, you can get pretty far on straw men and Gish gallops.

Anyway:

We’re (Americans) in a situation where we’re faced with an active and armed fascist movement, and those who would oppose that movement have systematically disarmed themselves because “guns bad”.

If we basically have to worry about warlords wandering around killing people at will then civilization already is done.

What’s your plan for when they decide to remind us that “political power grows out of the barrel of a gun”?

I don’t plan my life around everyone being raptured away, aliens landing or civilization completely breaking down. It’s irrational to make real sacrifices or do things that require a meaningful tradeoff/risk to avoid such unlikely events.

What’s your plan for when they decide to remind us that “political power grows out of the barrel of a gun”?

I’m pretty sure Mao didn’t mean “If you have a gun, you have political power” with that quote. The original quote was “以后要非常注意军事，须知政权是由枪杆子中取得的”. It’s not talking about random citizens with guns, it’s from the perspective of leading/governing countries.

It’s not really practical to train models on CPU. So basically your options are to get a GPU or to rent time on someone else’s server that has the necessary compute. GPU VRAM seriously determines the sizes of model you can train, so renting a server is probably the more flexible option. It generally needs a lot more VRAM to train than to simply run a model.

Just an example of a place you can rent GPU time from: https://vast.ai/pricing

Even for a very powerful GPU like an A100 with 80GB VRAM the prices aren’t that bad. It’s like $2-3 per hour.

I don’t know what their position is either, but “arming up” isn’t going to do anything against a modern, relatively competent military. Back in the time the second amendment was written (as an example) there wasn’t that big a disparity in the resources the military could use and normal people. The citizens were less organized but had numbers on their side.

Today, there is absolutely nothing you can do with a gun vs drones, bombs, planes, etc. The only way you really prevail is if the government isn’t willing to slaughter its own citizens and guns aren’t helping there at all. In fact, the opposite may be true since it makes it easy for the government to label the people shooting at their officials as terrorists.

But that’s a different problem from “was the contract even signed?”

I was responding to the “it wouldn’t have ended up in court unless a misunderstanding occurred” part. My point is the fact that it ended up it court isn’t necessarily because there was any misunderstanding at the time. People don’t always act in good faith.

I can see how a thumbs up can be taken as a signature, if both parties understand that. Since this ended up in court, they obviously didn’t.

Uhh, there are definitely other reasons it can end up in court even if everyone understood everything perfectly. For example, if at any point one of the parties decided it would have been in their best interests if they hadn’t agreed to the contract…

Pasting an error code or cryptic log file message with a bit of context and it’s better than googling for 4 days.

I usually can find what I’m looking for unless it’s really obscure with days of searching. If something is that obscure, it seems kind of unlikely ChatGPT is going to give a good answer either.

If you know enough to sus out the obviously wrong shit it produces every once in a while.

That’s one pretty big problem. If something really is difficult/complex you likely won’t be able to tell the difference between a wrong answer from ChatGPT and one that’s correct unless it just says something obviously ridiculous.

Obviously humans make mistakes too, but at least when you search you see results in context, other can potentially call out/add context to things that might not be correct (or even misleading), etc. With ChatGPT you kind of have to trust it or not.

Double Arch BTW. Feels great!

Does Rust count as the Arch Linux of programming languages? If so, you can put me down for a triple.

That’s 70m people oblivious (or cognitively dissonant) to Meta’s very well documented past transgressions and abuse and exploitation of people’s data.

It’s probably mainly people that are already on Twitter and/or Facebook so they’re not really giving up anything new. To be honest, at this point I’d probably be more willing to trust Zuck with data. At least robots are relatively predictable, Musk seems unhinged.

The neoliberals are just going to move from one platform to another.

Huh?

Also, ChatGPT 4 came out but is still only available to people who pay (as far as I know). So using ChatGPT 3 feels like only having access to the leftovers. When it first came out, that was exciting because it felt like progress was going to be rapid, but instead it stagnated. (Luckily interesting LLM stuff is still happening, it’s just nothing to do with OpenAI.)

Dear murderer,

Please don’t murder me. I’m asking nicely and I would appreciate it if you could respect my preference in this matter.

Best wishes,

Potential Murder Victim