thanks

It’s like you bought a car and deliberately hit the wall to make a headline “cars make you disabled”. Or bought a hammer, hit your thumb and blame hammers for this.

Guys, it’s a TOOL. Every tool is both useful and harmful. It’s up to you how you use it.

I’m reading comments on arstechnica and seeing people mad at… what exactly?

The reason I go to web search is to answer my questions. Now it’s given to me at once, without need to go anywhere. Is it sometimes hallucinating? Of course it is, but have you really 100% trusted information on the Internet before anyways? I haven’t.

You say that ads driven websites are going to stop receiving money. But have you really liked ads driven websites? The same ones whose main incentive is to keep you on the website as long as possible or, in fact, wasting as much your time as possible to sell it to ad companies? The ones that were really worth visiting already changed their business model.

I was talking mostly about side projects. I don’t have much time for them right now. Thanks to LLMs, I can spend those few hours a week on doing instead of reading what is the best way to do X in ever changing world of web front-end frameworks. I just sit down, ask: “how is it usually done?”, tweak it a bit and finish.

Example: I have published an app on flathub a while ago. Doing it from scratch is damn complicated. “Screw it” is what I would say in pre LLMs era after a few hours ;)

True and not true at the same time. Using agents indeed often don’t work, mostly when I’m trying to do the wrong thing. Because then, AI agent does not say “the way you do it is overly complicated, it does not make any sense”, but instead it says: “excellent idea, here are X steps I need to do to make it happen”. It wasted my time many times, but it also guided me quickly though some problems that would take hours to research. Some of my projects wouldn’t have been finished without AI.

To that end the company is developing a “Pay Per Crawl” system, which would give content creators the option to request payment from AI companies for utilising their original content.

So Cloudflare is not as much “saving the Internet”, as just becoming a middleman between LLM training companies and content creators. Which I believe has a potential of being a true goldmine in the future.

ofc I could even send raw api requests, but sometimes it’s good to have a nice GUI that “just works”.

Specifically I’m looking for something that could handle not only text responses, but also attachments, speech recognition and MCP support.

Taking advantage of the fact that this thread became popular, question to all of you guys: do you recommend some other open source LLM front ends?

As long as they are free and open source, I don’t care.

+1, I came here just to paste a link to it

Honestly, I thought Meta talking about Fediverse integration was just marketing bullshit. Are they really doing it? 🤔

For start definitely Linux Mint. It is stable, has strong support, works out of the box.

I have also heard uploading (seeding) is where you really get in trouble

Which is interesting since modern web standards make it possible to exchange data peer to peer in browser. Isn’t PeerTube working this way? So you might not even know you are sharing. How does it work in such situation?

Thanks, that might be helpful. Is this bug related to VirtualBox installation or Raspberry Pi?

Have you reported this bug somewhere? It might be a good idea to let nixos team know this problem occurs

For now I use Mint + etckeeper + Timeshift as a form of backup, but I have never had a courage nor need to “try it” and actually restore state 😆

My dream is to have entire operating system state stored as configuration, tracked by a git repo. To be able to know exactly what changed when, to revert back to whatever state I want and quickly copy setup from one device to another. So naturally NixOS caught my attention. I tried it before, once on Virtual Box VM and once on Raspberry Pi and I failed with installation of it on both of them, my weekend was too short :D It was a few years ago, it might get better now.

Isn’t profile management introduced like right now in the same release?

I have read this post’s description and didn’t even open a link, since it didn’t sound interesting. But two big features are introduced in this release: **tab groups and profile management **

Why do everyone emphasize the fact that it is Rust based? What difference does it make? Personally, I don’t care whether it’s written in Rust, Cobol or Brainfuck. Badly written software would be buggy no matter the language.

To be successful, Firefox should not only try to keep up with the competition, but also offer some unique features that would attract new users.

I agree that LLMs are overhyped, but in my opinion they are quite good at summarising text. We all hate clickbait titles, and this feature has the potential to actually combat them. And what’s unique about Firefox’s approach is that it’s truly private. No other browser offers this.