News for hackers. Stuff that matters.
Re:OpenCode Browse by bob1029 on Monday November 16, 2026 @08:31PM (#50526246)
I don't understand the need for this. A strong reasoning model already knows how to use Powershell to launch my browser with my profile. gpt-6.1-terra will build a whole goddamn .NET project with playwright just to pull the showtimes from the local cineplex.

Shell execute and apply patch are the only two tools you need if your reasoning model is powerful enough.

Re:OpenCode Browse by thund on Monday November 16, 2026 @09:01PM (#50526458)
One situation I found is "AI: it works on my browser" - "User: not on mine" -> and "AI: ok let me connect to your browser so I can run some test".

It's scary but effective - the alternative is a continuous copy&paste of logs from the dev console

Re:OpenCode Browse by bob1029 on Tuesday November 17, 2026 @01:48AM (#50528251)
[delayed]
Re:OpenCode Browse by meatmanek on Tuesday November 17, 2026 @01:21AM (#50528079)
Are you burning tokens having your agent reinvent the wheel every time it needs a wheel?
Re:OpenCode Browse by bob1029 on Tuesday November 17, 2026 @01:45AM (#50528223)
A vast majority of my input tokens are cached. The cost of bootstrapping is amortized across many turns of conversation.