I got broke by just reading the title.

You don’t have to buy more RAM in order to benefit from this change. Your existing one should be enough. Usually if your system needs more VRAM, then there is most likely still some system RAM left to use it as an extension.

It’s not on Flathub, because of Ai generated code and other assists maybe? https://docs.flathub.org/docs/for-app-authors/requirements#generative-ai-policy

It didn’t. They were just afk.

Why does everything need to be done with an LLM?

What makes this Chatbot client different from just using it in the browser? My first thought was, it might get special permission to better interact with the system, like the agentic tools do. I assume it can better integrate into system with the taskbar maybe. Or maybe this is more efficient than just running the webbrowser. Or it might have special commandline arguments with special options?

Oh… wait its just an entire browser running a single tab. Alright then. Why does this need to be an app on its own? To me this is as useless as a native browser based Discord app… Just bookmark it in your browser and open it there. You can even customize it even more with browser addons.

When you make changes to the comments or pseudo code to maintain the program, then you also need to do the same changes to the actual source code the compiler will use. As the human language comments need to be compiled to C by human, right? And this would end up thinking and maintaining the source code of two languages and hope they always align in their logic.

I never did this approach and only get this from reading the blog post.

So just write more tests and a Test-Driven-Development (TDD)? Someone has to engineer these tests too. How does the simulation software (which itself needs to be developed and updated) know all behaviors of a system, that is relevant to it? You basically ask if we someday could have a magic box that does all of that for us.

I don’t think that most will abandon in the future, as the Ai even becomes better and most people only look at the surface. The biggest problem (besides the unethical training data and not respecting licenses from the original data) is if you don’t know what it produces and don’t check it without understanding. Where it can be useful is aiding in code analysis, but not replacing it. And most will shift to local available models (I hope so), as local hardware becomes better at it too.

I’m not the biggest fan of Ai at all. But I don’t see a reality where Ai disappears in the future, unless every company is doing it gets bankrupt. Looking at Microsoft and Nvidia, this sounds unreasonable. Because if one major player like Anthropic goes down, another one will rise up, maybe from China.

Ah! I’ve seen a few times some artifacts with my RX 7600 on KDE too, but not on max/min, but randomly. I couldn’t reproduce it, so it is really hard to talk about such subject. As it just recently started (I’m on 7.1.6), I guess this is the same issue. Wondered if this is an issue with KDE or Krohnkite extension or my GPU dying.

So glad it’s “just” a bug in the Kernel. This is just a visual issue right? It doesn’t hurt I hope.

Official Bash documentation (should be the same for ZSH too I guess): https://www.gnu.org/software/bash/manual/bash.html#History-Expansion

“The Problem with Linus Tech Tips: Accuracy, Ethics, & Responsibility” (44:14mins) by Gamers Nexus on August 14, 2023: YouTube or Invidious or Internet Archive

This video is not monetized. This video covers our serious concerns regarding the data accuracy of Linus Media Group, including Linus Tech Tips, ShortCircuit, and TechQuickie, particularly as it relates to rushing content out the door to favor – by staff’s own admission – quantity over quality. As the company continues to expand into its LTT Labs direction, the importance of accurate data increases; however, even as ‘only’ entertainment, there are still certain responsibilities to the consumer and the manufacturers to report fairly (and to have defined corrections processes in place). We tried to approach this as objectively as possible and hope that viewers are able to listen to the evidence we present, particularly as it relates to significant and frequent data errors that now present in nearly every technical review video.

TIMESTAMPS

00:00 - The Last 2 Weeks
01:40 - LMG is Rushing Too Much: Establishing the Premise
03:48 - LTT's Own Employees Agree
06:58 - This Isn't "Drama" & Risks
09:05 - Bad Data from Linus Tech Tips
10:12 - GPU Review Errors
15:02 - CPU Cooler Test Errors
19:09 - PSU Review Errors
19:53 - CPU Review Errors
22:39 - Asterisked Errors
26:15 - Ethical Concerns: Irresponsible Actions & Conflicts
28:21 - Ethical Concerns: The Review of Billet Labs
34:49 - Ethical Concerns: 'Not-Review' of Pwnage Mouse
36:53 - UNACCEPTABLE & The Community is Disturbing
39:22 - Unfair to Consumers, Manufacturers, & Reviewers

New video after Linus Tech Tips responds: https://www.youtube.com/watch?v=X3byz3txpso (only from 00:48 to 12:57 part)

Probably to warn any readers coming across this post.

This happens if you are that dependent on Ai tools. It would be less of a problem running offline models on your own hardware, so you don’t have to pay for subscriptions or tokens.

The difference of a private chat with an Ai to a public question on Stack Overflow (or any forum for that matter) is, that on Stack Overflow multiple persons can read and comment. Answers often iterate and fact check if someone hallucinates, because so many eyes sees it. If the answers are helpful is something everyone has to decide themselves, but the principle of an open platform being very useful is undeniable.

Compare this to your private Ai chatbot. Only one person sees the answer and if something hallucinated is in there or the quality of the answer is not good, then you might not know. And those Ai bots are controlled by the few big corporations, maybe a little less if you use a custom offline bot, but they are probably not as good as the big models. That’s why this is a bad trend. I think the open and user controlled Stack Overflow was a better approach, by principle.

LOL oh thanks haha, I indeed didn’t know. xDD

Thanks. :-) Maybe people think I was trying to be mean or so. At least it stays at 67% upvote ratio somehow, haha:

Because you don’t want a single operating system manage the entirety of the Rust eco system. They need to be its own thing, so it can be used and managed by an individual team independent from any operating system.

No, read again what I explained before. I explained the technical problems of the architectural flaws. There are deep problems with LLMs and I explained why some people have a problem with it. You might not care, but that doesn’t solve the problems.

There is a difference. I explain why you are dishonest and misleading. I don’t just accuse. So its based off technical reasoning and not just personally attacking without reason. You just have no arguments left and just attack personally instead basing off on reasoning. That is a huge difference.

Unless you have good arguments, LLMs have architectural flaws in their design and need to change. And that is a factual correct statement, which I explained earlier. That has nothing to do with an opinion.