Bez: Generating a browser engine from specs and tests

nerdypepper 103 points 44 comments October 01, 2026
tangled.org · View on Hacker News

Discussion Highlights (9 comments)

fouc

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.

Alacart

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.

mircerlancerous

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

helpprotactiniu

Is this named like Jev intentionally? Or is this just a new naming convention that I haven't been watching?

trencedamp

But can it dance

amelius

Ok, but will you be able to understand the code?

amelius

Can we do the same for MacOS, iOS? I want to run them inside Linux.

esprehn

Very cool idea, though I think we're a long way away from this. Hopefully they file bugs on the specs when they find ambiguities. Also the specs are written to define observable behavior, and there's a fair bit of ambiguity that's UA defined, but to be actually compatible with the Web requires doing what Chrome does. The good news is that you can look at the source of the 3 major engines (and Ladybird!) and your AI agent can do comparisons and figure out optimizations.

tannhaeuser

Tried this (a CSS renderer specifically) two years ago, but the LLMs at the time weren't up to it and would either pull-in external libs or tell me "it's a very complex task" and generate a mere skeleton for a simplistic case of default layout.

Semantic search powered by Rivestack pgvector
8,245 stories · 76,959 chunks indexed