Transformers.js allows you to run models right in the browser. The fourth version focuses on performance. The new version has support of WebGPU and it opens new era in browser-run models
It's just a surprise to see what can be done with the models in browsers today. This demos shows the abilities of the models, and this is the time for creators to bring their ideas and make solutions for real tasks
This release also adds new models to be run in browser Mistral4, Qwen2, DeepSeek-v3 and others. It has limited number of changes, what makes it pretty stable for a major version
While the idea is somewhat new for today's JS. And I see some benefits for this to make single-purpose servers compiled into tiny binaries. I believe it would take some time to make this popular. You should to find the niche where it's required right now. And also I would spend more time working on marketing: explainer,
documentation, landing page. For example now the readme looks too ai-written
What's about code and DX: it's not a good practice to export anything using globals, this is what JS world refused to do long ago. It turns your code into a hardly debuggable mess quickly
I think it's would be faster to build this as a Discord community and then to move to a dedicated app/service. It's too early to fix anything into a profession or term because things are changing too fast. And community would help you to structure the information faster
Builders will be there as long as people do programming. But it's the first step to move to better builders. Or to standard one?
Also it helps to start with typescript faster and easier, and to make the learning curve smoother and maintaining less complex for all developers on all platforms
If one of developers changed function name and the other changes alignment of parameters in the same line, this tool would recognize the changes and merge this line without conflicts. Regular git algorithm would turn it into a conflict because the changes happened on the same line
Ok. We are talking about different things. There are fundamental rules which make technologies to strive or disappear. But there are other fundamental rules for products, features, etc. So you talk about products and I talk about technology.
YCombinator is about products, not technologies, so their example is not suitable here. Agents is a technology. They have fundamental advantage over premade software. They are already here and they are doing valuable work. They will stay for the near future. You can argue against reasons to use particular agents or particular products built around them, or particular features, but not against the whole technology.
The technology is verified, we need to find the way to make it safer and more sustainable. This would require to solve many technical tasks: build safeguards, create eco-friendly energy production, solve explainability, build physical infrastructure, develop new technical standards, etc.
Well, the history of software development shows that everything is changing and don't lasts forever. Golden age of SaaSes now is going to fade (at least for current version and for some time, maybe a decade). Today junior developers can create a fully working SaaS with dozens of features without even knowing how it works. And they would spend a few weeks or evenings to develop it. We are about to see a flood of services and it will make all the business model obsolete. This is what is happening now at Github. You can see a lot of excellent projects which were written by AI, and no one wants to contribute to these projects, because they can do the same project on themselves
You can do a blog about retro programming to find clients which have your stack. I read about group of developers who were writing in Cobol in 2010s. Because this software were in use and still in use somewhere. The guy who wrote about it was a developer with decades of experience, but no one wanted hire him because of the age. Then he found other developers in the same situation and run a company to support software written in outdated languages
You can write old-styled software for those who have nostalgic feelings about good old times, or support solutions written for old platforms. Instead of been thinking about it as of trash, think about it as it is retro
There a lot of examples of things been critisized in the beginning and strived, there are a lot of things which have gone. It only means that there could be only reasonable critics. Can you say if your criticism is reasonable? I saw a lot of things being thrashed in the beginning. And these things people use everyday. You can choose from thousands of examples
First plane didn't have cockpit, and windows, could fly only hundreds of meters, and looked more like a clothes dryer than a plane. Someone could call it inefficient (and really it wasn't efficient). It was easy to call it dangerous. But as we can see, planes evolved since then. When the first radio was invented there was no radio station to listen. When the steam train was invented it was crazy expensive and there was no government which has enough money to build all the railroads we have today
All of these technologies were modified by talented people, some of them were inventors, others later adopters. But they changed how this technologies work, and what goods they brought to us
AI is too young technology to tell if it fail or not. You can critisize it or you can change the direction of the progress. It's up to you
The only thing I'm failing to understand is why you are using my arguments against my point of view, while you are who's critisizing agents. Can you elaborate your statements then?