[mikepurvis]

I think it's taught to look at source code through a peephole for the sake of context preservation, but I feel like this could be a good use-case for some sub-logic or even a full sub-agent. Like, here sub-agent, you skim that file and tell me a summary, and highlight any areas related to X and Y so that I can look at them in my main context. You can also periodically observe the main work stream and interrupt me if you realise that something in the file you're thinking about is relevant to what I'm working on or might change the direction of what I'm doing.

[robertkarl]

One thing you can do is offload from Claude to a dumb local model for summarizing. Local LLM sub-agents.

[sinsudo]

I think what you suggest is like a local second order approximation, that can help. But, I think that the real problem is a global one, is about architectural taste, how the many local pieces interact and their friction. Currently that demands human expertize.

[Terretta]

> I think it's taught to look at source code through a peephole for the sake of context preservation

Yes, to a (real) fault. Less than one in fifty times it ignores an instruction or piece of data in a file has it seen the instruction or data before ignoring it. The other times, it's done this sampling nonsense.

Results are night and day using the 1M token models and reading the full files.