points by NewJazz 3 days ago | 0 comments
On purpose? I was using qwen3.8-27b the other day and very quickly ended up burning through half of the context (it has 128k total) pretty quickly. Not because of my directions, but simply because the codebase was very large.
[–] tepmoc 3 days ago
[–] NewJazz 2 days ago
Yeah codebase structure is very important. Admittedly, by large I mean average size but very poorly structured with a spaghetti (and sometimes cyclical) import graph.
[–] zahlman 3 days ago
Is there a straightforward way to check the current context window usage in the web chat interfaces, btw?
[–] rockdoe 2 days ago
In Claude it used to be the circle on the lower bottom, but now it's a bit more hidden and you have to expand the sidebar.
[–] NewJazz 2 days ago
I don't know, I usually use Pi.
At least this my discovery when I did evals on my reviewers skills. 10k LOC is high end for high effort or around 150k context using opus. You can push towards 15k but that’s on max effort with about 400-500k ctx.
Fast models like haiku do not even need 1M ctx in my view