Re:Scaling long-running autonomous coding
by gordonhart on Wednesday January 14, 2026 @06:24PM
(#46625490)
Web browsers are insanely hard to get right, that’s why there are only ~3 decent implementations out there currently.
[ Parent
| on HN ]
Re:Scaling long-running autonomous coding
by qingcharles on Wednesday January 14, 2026 @11:51PM
(#46628196)
The one nice thing about web browsers is that they have a reasonably formalized specification set and a huge array of tests that can be used. So this makes them a fairly unique proposition ideally suited to AI construction.
Re:Scaling long-running autonomous coding
by pleurotus on Thursday January 15, 2026 @02:21AM
(#46629200)
As far as I read on Ladybird's blog updates, the issue is less the formalised specs, and more that other browsers break the specs, so websites adjust, so you need to take the non-compliance to specs into account with your design