Hacker News
points by ethanj8011 4 days ago | 0 comments
> 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.

[–] nfw2 4 days ago
having an index of the code that the agent can use to find what its looking for instead of grep seems to work wonders
[–] gnatolf 4 days ago
That crucially depends on what the index achieves. What do you aim for? Just lookup of symbols? Architectural information? Data flow systems?
[–] xyzsparetimexyz 4 days ago
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.
[–] desterothx 4 days ago
I hate that they claim the pricing like that. It's 22.5e, we show our prices VAT included, not this misleading american bs