zlacker

[return to "Scaling long-running autonomous coding"]
1. trjord+l6[view] [source] 2026-01-14 22:42:42
>>samwil+(OP)
This is going to sound sarcastic, but I mean this fully: why haven't they merged that PR.

The implied future here is _unreal cool_. Swarms of coding agents that can build anything, with little oversight. Long-running projects that converge on high-quality, complex projects.

But the examples feel thin. Web browsers, Excel, and Windows 7 exist, and they specifically exist in the LLM's training sets. The closest to real code is what they've done with Cursor's codebase .... but it's not merged yet.

I don't want to say, call me when it's merged. But I'm not worried about agents ability to produce millions of lines of code. I'm worried about their ability to intersect with the humans in the real world, both as users of that code and developers who want to build on top of it.

◧◩
2. virapt+Ik1[view] [source] 2026-01-15 08:21:33
>>trjord+l6
> Web browsers, Excel, and Windows 7 exist, and they specifically exist in the LLM's training sets.

There's just a bit over 3 browsers, 1 serious excel-like and small part of windows user side. That's really not enough for training for replicating those specific tasks.

[go to top]