Comment by ethanj8011
9 hours ago
> For me, around 200,000 or 300,000 is where I start looking. I’ll check, see it’s at 250,000, and think: I’ve got a big job coming up. I’m going to reset and start fresh
I don't find this to be true, at least with the newer models. I also find that the models fill up to 250k very quickly (presumably mostly by looking through the codebase). Without that context I find the models perform badly. I also don't really notice that large of a change until around 700-800k context and even then it isn't as bad as it used to be. I suspect, that (especially for coding), the long horizon RLVR tasks have helped with this quite a bit.
For me, it's about getting the most work out of the €18 anthropic plan as possible. That means avoiding letting the context go over 300k or so.
having an index of the code that the agent can use to find what its looking for instead of grep seems to work wonders
That crucially depends on what the index achieves. What do you aim for? Just lookup of symbols? Architectural information? Data flow systems?
[flagged]