Yeah 60k is ludicrous, I've barely seeded the context at that point and I don't see context related degradation until well into the 600-700k.

▲

qsera 4 hours ago | parent | next [-]

In this thread: People tossing coins independently and fighting over the result they got.

▲

kuboble 3 hours ago | parent [-]

No it's not.

It seems that people have different workflows or repos, or memories or prompts or expectations.

	▲	diab0lic 2 hours ago \| parent [-]
		For what it’s worth, as a third party I read your and qsera’s comments as saying the same thing.

▲

embedding-shape 5 hours ago | parent | prev | next [-]

> I've barely seeded the context at that point

I think that's issue, rather than 60K being small.

Most of the actual edits/changes I request to codex are solved within 100-150K tokens, beyond 200K I'd definitively try to restart the session as soon as I could as all models are horrible once you get across ~20% of the total context size. And this is while working on +million LOC codebases.

Problem I guess is that there is no solid and concrete evidence of this (to me [and others seemingly] obvious) degradation, but should be easy to prove, yet no one has time to sit down and show it :)

But the likelihood of a model getting minor details wrong once you're above some magical threshold between 15-20%, seems to skyrocket, and I hit that issue sufficient amount of times that now my workflow is trying to prevent that.

▲

rtpg 2 hours ago | parent | prev [-]

what are y'all doing to hit that? Do you just not give it any pointers and let it churn away? What kind of context are you handing off?

I routinely get claude to do things pretty decently and finish up easily in the 4-5 digit range of tokens. It seems to be doing the right kind of thing to not waste its time looking at 1000 files.