This makes a ton of sense to me with the huge corpus of web standards that exist. In theory we should be able to generate a browser from those specs, it just took a massive amount of effort before. Maybe if things like this get some traction, some of the human time spent implementing the spec could be spent on creating more/better specs, allowing for even better generation too.
Edit: replies are making good points about AI capabilities and where the effort really goes. Let’s just say that I meant this in an aspirational sense, rather than where the rubber actually meets the road today.
As someone who has spent the last 3 years implementing a browser engine from scratch full time (that currently passes ~half the 200k "css" tests that test style/layout/rendering), I find that (without a lot of close hand holding) the AIs are very far from being able to do this. They'll give you something that passes the tests, but it will do it a ridiculous way be far too slow to be useful (and is wrong architecturally such that it's not going to converge on a better solution).
I think browser performance (and security) improvements are really difficult to tackle at the scale of browser complexity, and are both art and engineering. In other words, if this were possible, we would see the results first in existing browsers. This project is very interesting though.
> In theory we should be able to generate a browser from those specs, it just took a massive amount of effort before.
No, not really. The absolute vast majority of those specs are human technical and technical-adjacent language, not machine-readable specs.
On top of that many web often invent new terminology because a lot of things are specced years or decades after something popular has taken over the term in userland.
I'm sure this is not the origin, but Bez is a celebrity in England, a member of a 90s band called happy Mondays who didn't sing or play anything but just danced. Famous on the panel show circuit
This makes a ton of sense to me with the huge corpus of web standards that exist. In theory we should be able to generate a browser from those specs, it just took a massive amount of effort before. Maybe if things like this get some traction, some of the human time spent implementing the spec could be spent on creating more/better specs, allowing for even better generation too.
Edit: replies are making good points about AI capabilities and where the effort really goes. Let’s just say that I meant this in an aspirational sense, rather than where the rubber actually meets the road today.
As someone who has spent the last 3 years implementing a browser engine from scratch full time (that currently passes ~half the 200k "css" tests that test style/layout/rendering), I find that (without a lot of close hand holding) the AIs are very far from being able to do this. They'll give you something that passes the tests, but it will do it a ridiculous way be far too slow to be useful (and is wrong architecturally such that it's not going to converge on a better solution).
I think browser performance (and security) improvements are really difficult to tackle at the scale of browser complexity, and are both art and engineering. In other words, if this were possible, we would see the results first in existing browsers. This project is very interesting though.
> In theory we should be able to generate a browser from those specs, it just took a massive amount of effort before.
No, not really. The absolute vast majority of those specs are human technical and technical-adjacent language, not machine-readable specs.
On top of that many web often invent new terminology because a lot of things are specced years or decades after something popular has taken over the term in userland.
I'm looking forward to the day when we have fully functioning web browsers that we have full programmatic control over in all aspects.
With luck all chromium/blink-based browsers will go the way of the dodo bird.
I'm afraid internally they would still look like chromium/blink anyway.
This is a neat idea. It opens up a whole new way to make a web app into a native app, while also adding native features not available in web views
But can it dance
Is this named like Jev intentionally? Or is this just a new naming convention that I haven't been watching?
I'm sure this is not the origin, but Bez is a celebrity in England, a member of a 90s band called happy Mondays who didn't sing or play anything but just danced. Famous on the panel show circuit
Maybe it’s one of those weird LLM smells, like the OpenAI goblin problem.
https://openai.com/index/where-the-goblins-came-from/