So you don’t know what you’re talking about any more than I do and there is nothing I can learn from you. Why didn’t you say so in the first place instead of wasting my time?

Why do you think I’m sure? Do questions assert certainty?

You write as if you know what happened and why Welsh is dying out. Answer the questions then instead of whatever moral grandstanding you’re doing.

How long have Welsh people have internet? How many Welsh people have and had the means to archive the language, maybe even try and popularise it? How long was the Welsh government held back from (and probably they were) from teaching it a schools? Did nobody have the chance to create free, accessible Welsh courses for anybody to access? How many Welsh people that could speak it made an effort to teach their kids and others?

There are options to keep language alive. I can understand it being wiped out (many examples and ways to do so), but if it survives and the people speaking it don’t make an effort to spread it, modernise it, and adapt, then it is also self-inflicted. Look at the Baltic countries. Estonia tries to keep up with the times and allows the population to vote on Estonian words that should enter their dictionary instead of the anglicised ones.

Of course the English banned it in school look up Welsh not.

Your rage made you a word. What?

I ask a fucking question?

Kinda self-inflicted isn’t it? Or did the UK ban Welsh at schools?

Lol, so because Anslopic train on proprietary and security sensitive data, it had to be blocked. I think that exposes the problems with how they retrieve their training material and where they get it from. Maybe the paid prompts which shouldn’t be used for training are being used after all? Who would’ve thought!

I worked on desloppifying a codebase, but had to do with AI. This was a job. Spec driven development didn’t work on that project but targeted refactors did.

Setting up a project to work with AI is not easy, IMO. You need rules, and skills, and commands, and whatever else they call it in order to be productive, otherwise you spend your time fighting with the the AI.

You’re right to question 10x and 100x productivity gains. Those only exist if you’re not willing to look at the code. I’ve had people tell me “code isn’t important”, then run into issues, and ask me to help out. The code was indeed important. Therefore, how you use AI is the important part here.

Using AI to write the entire codebase is cute. It might get your project to MVP very quickly and then you have to hire somebody who knows what they’re doing to fix all the stuff in it. I would recommend using it in a targeted manner:

• ideation
• code analysis
• targeted refactors
• boilerplate
• mini features
• bug detection

As an example, connecting an AI to an MCP like Ghidra for working with decompiled binaries is impressive. You do have to stay on your toes all the time and verify what it says, but it changes the while experience.

Once you let it loose to make bigger changes, it will inevitably fuck up while spitting out reams of code at you. Reviewing all of that is the bottleneck because it requires Actual Intelligence. Using another Artificial I to review what the previous AI did is only useful for bug detection or exploit detection (in my experience). For architectural mistakes or clean code (whatever your perception of that is) has only lead to pain for me.

So yeah, not 100x, not 10x, but maybe 1.1-1.5x. More if you’re careless or don’t know what you’re doing and Just Want It To Work ™️.

I don’t know what kind of a GUI you’re building, but there are simpler options than Tauri out there. Slint comes to mind.

Welcome 🙂 We hope you continue enjoying it!

Pro: it’s GLOSS - Gratis Libre OSS.

Con: it’s run terribly. The Linux foundation could be doing a much better job. 1-2% of its funding go into the linux kernel.

Thanks for having a look!

Thanks for having a look!

It is primarily sponsored by the government of Switzerland 🇨🇭 where it is currently deployed for citizens.

Now this, I like!

Github, not so much

It requires superconduction. To have something like that sitting at home, we either need to cool it down like crazy or material science has to advance to the point where we have room temperature super conductors. So, while a impressive advancement, it probably won’t be in our living rooms, in our desks, or in our pockets anytime soon.

But when we get that room temperature superconductor, at least we’ll be ready!

Is the bubble close to popping? What are these bullshit deals?

The entitlement is strong in that one!

Thanks for pinging them.

Good for you for not using AI. If you want to assume unpaid responsibility for your project, go ahead. Doesn’t mean everybody else will or should.

Amazing. Thanks for the link.