AlisaYoki

Why does it makes building web apps fun? I would try it, it sounds interesting!

I ask the AI to monitor this on its own; my agents have automatic reminders once a week - to check all the code for technical debt, suggest solutions, and sort tasks by risk and complexity. And, in fact, this helps me not to overlook anything.

Wow!!! Interesting product! Thank you for sharing :)

When people make applications with AI, they say that I made an application (although in fact the application was made by a AI). Or when a person goes somewhere on a horse - he says "I rode as fast as I could" - but he didn't make the whole work actually, that’s all was made by horse

I think there is the same logic :)

To the question “why?” the answer is obvious: 1 — why not, 2 — because it’s beautiful. Projects like this remind us that programming is also an art, not just about solving business problems. Thank you for sharing, it made my day :)

What do you mean by “AI”? Artificial intelligence is a program, a program cannot pay taxes for itself—that’s against the rules. But companies that create AI and those that use AI must pay taxes. Like, they’re just like any other companies — why should they be somehow separated from them? :) And it seems that AI companies are earning enough to support the country’s budget quite well through taxes, providing citizens with better conditions — all for the greater good :)

Hahaha, that’s brilliant, I’ll definitely try it sometime

Interesting article, thank you for sharing!

This isn't pillaging, this is the logical conclusion of open web plus AGI race. You can't have both unlimited access and zero cost, someone always pays and right now it's volunteers... Tomorrow it'll be the users who can't access Wikipedia because the servers are down

You have been giving content for free for AI training for years, and now you complain that the AI came to pick it up? You will decide whether you are public or a commercial service…

What do you mean? Are there any official articles where I can find it?

Great idea, but how do you guarantee “no-account needed” security? Even if the code runs on the client, browser extensions (such as malicious plugins) or a compromise of the CDN from which your script is loaded can easily intercept this data. Trusting the “browser” when it comes to the security of client data is an oxymoron. How do you plan to convince paranoid security experts that your website hasn’t been compromised?

It seems like a logical story: if something doesn’t work out, you need to look for other ways to solve the problem. There are many applications, and you need to check them all. Those who care about their product and who knock on every door come forward - with this approach, they’ll definitely get a response

20 years ago, if you had a good understanding of such an innovation as the “internet,” all doors were open to you; you could do much more than the average person and, accordingly, achieve more. Now, however, it’s the time of AI, and I believe the same principle applies here. Whoever is the best at working with them has the power

P.S. But I’d also teach them how to communicate politely with neural networks, haha, just in case (and, well, overall — what does it matter whether it’s a person or a machine? It’s like you should always try to be kind and polite…) :)

What a sweet comment, haha

It seems that solving such a problem, which has been going on for a very, very long time, will be very difficult. Do you think this is realistic?

Why do you think that work won’t be well‑paid in the future either? I don’t really understand

Of course, you need to have critical thinking and try not to blindly hand over all your data to large platforms, but it’s as if you want to trust what you’re using. Otherwise, it’s just like if every time I wanted to eat a sandwich, instead of just eating it, I also took indigestion pills just in case — it sounds super inconvenient and, well, unnecessary.

Could there have been some kind of data leak involving German companies? I mean, the services track those who are in Germany and leak their data.

Hahaha, I thought about that too, I have to admit, it’s a really great idea

I think this is a great story. I’m currently working simultaneously with a Grok bot and a Cursor, and it’s very convenient when you assign a task to one Grok bot agent, and they handle communication both with their own agents and with the Cursor agents. They set the requirements themselves, check the results, and so on

I use Cursor, and in fact, their internal models are more than enough for me. Especially considering that Grok bot has recently been released; it has its own limits and also helps save Cursor tokens (by properly drafting technical specifications and making edits to tasks). I pay $60 per month for the subscription, sometimes $200 if there are a lot of technical tasks

It seems that in the age of social media, the best way to build an audience cheaply or for free is to post as many short videos as possible on TikTok, Instagram, and so on :) But it will be interesting to read about other methods as well.

I have a small travel application with a tiny budget. The assistant of norms turns a dirty list into a skeleton of a trip and a list of things, but not as a source of visa rules and geography. As a result, we took the facts out of the model: POI either ground or throw away, knowledge cards were made from the URL to the original source, added the ability to edit the trip without a new pompt. Chat is just a login, and a product is an object that can be checked

I think it will become deeply integrated into all spheres of life, and we won’t be able to imagine life without it (just as we can’t imagine life without the internet now). People get used to convenience.

Fair. The agencies are one tool, but the payment intermediary is usually the one that actually moves - a chargeback often does more than an ECC complaint ever will