zlacker

[return to "Scaling long-running autonomous coding"]
1. jphowa+E4[view] [source] 2026-01-14 22:36:08
>>samwil+(OP)
The browser it built, obviously the context window of the entire project is huge. They mention loads of parallel agents in the blog post, so I guess each agent is given a module to work on, and some tests? And then a 'manager' agent plugs this in without reading the code? Otherwise I can't see how, even with ChatGPT 5.2/Gemini 3, you could do this otherwise? In retrospect it seems an obvious approach and akin to how humans work in teams, but it's still interesting.
◧◩
2. nl+ms[view] [source] 2026-01-15 00:41:56
>>jphowa+E4
Generally they only load a bit of the project into the context at a time. Grep works really well for working out what.
[go to top]