[technocrat8080]

Curious about this too – does it use the standard context management tools that ship with Claude Code? At 200K context size (or 1M for the beta version), I'm really interested in the techniques used to run it for 30 hours.

[ChadMoran]

Sub-agents. I've had Claude Code run a prompt for hours on end.

[technocrat8080]

What kind of agents do you have setup?

[s900mhz]

You can use the built in task agent. When you have a plan and ready for Claude to implement, just say something along the line of “begin implementation, split each step into their own subagent, run them sequentially”

[fragmede]

subagents are where Claude code shines and codex still lags behind. Claude code can do some things in parallel within a single session with subagents and codex cannot.

[technocrat8080]

By parallel, do you mean editing the codebase in parallel? Does it use some kind of mechanism to prevent collisions (e.g. work trees)?

[fragmede]

Yeah, in parallel. They don't call it yolo mode for nothing! I have Claude configured to commit units of work to git, and after reviewing the commits by hand, they're cleanly separated be file. The todo's don't conflict in the first place though; eg changes to the admin api code won't conflict with changes to submission frontend code so that's the limited human mechanism I'm using for that.

I'll admit it's a bit insane to have it make changes in the same directory simultaneously. I'm sure I could ask it to use git worktrees and have it use separate directories, but I haven't (needed to) try that (yet), so I won't comment on how well it would actually do with that.

[s900mhz]

I personally do not do any writes in parallel but parallel works great for read operations like investigating multiple failing tests.