Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

OpenAI reduces Codex Model Context Size from 372k to 272k

github.com

Post reply on HN
Print view View original

171–180 of 194 posts

Re: OpenAI reduces Codex Model Context Size from 372k to 272k

#172

Post by wwind123 »

tekacs wrote: post #26

I know a lot of people like to say that compaction makes this moot, but the level of detail you lose across compaction is wildly too much for most things that I do, unfortunately. Perhaps if your plans don't have as much detail, or if you're not, for example, having a discussion with a lot of nitty-gritty then it's fine? The lack of long context is the main reason that I still end up using Anthropic. The worst is whe…

A typical suggestion is to make the agent create or update a .md file once in a while, so the agent would remember the new important things that have shown up since the last update. The problem is, how would the agent know which things are really important. If it knows that well, then /compact should work well too...

Re: OpenAI reduces Codex Model Context Size from 372k to 272k

#173

Post by crazylogger »

causal wrote: post #102
dannyw wrote: post #2

This was tweeted about when it happened, with some explanation from Tibo here: https://x.com/thsottiaux/status/2076543065045795309

Am I dumb or does this chart make no sense? Or why does the line only go up even with compaction? Or maybe "overall trajectory size" is hiding some meaning I don't understand?

The Y axis is total cost in USD. For it to go down would mean OpenAI refunding you money.

Re: OpenAI reduces Codex Model Context Size from 372k to 272k

#175

Post by PeterStuer »

tekacs wrote: post #26

I know a lot of people like to say that compaction makes this moot, but the level of detail you lose across compaction is wildly too much for most things that I do, unfortunately. Perhaps if your plans don't have as much detail, or if you're not, for example, having a discussion with a lot of nitty-gritty then it's fine? The lack of long context is the main reason that I still end up using Anthropic. The worst is whe…

All depends on context coherence. E.g. in Claude Code with the "1M context" models I am reluctant to push past 30%. So if that Codex 272K is 100% coherent than it is less of a difference. Still, even then the "hard fail" boundary has moved. Longer running agentic processes will surely run into this more often.

Re: OpenAI reduces Codex Model Context Size from 372k to 272k

#176

Post by PeterStuer »

anukin wrote: post #132
jwitthuhn wrote: post #120

Earlier quoted context omitted.

Claude does the same when you hit the context limit, but the difference is that claude's context limit is 1m and Codex's is 272k now. Claude lets you get a lot more done before you have to worry about the start getting compacted away.

Have you observed any decrease in performance at context higher than 200k? That used to be one of the major issues why clearing or compacting context when the context nears 150 to 170k is usually preferred.

I see it more past 300-350k these days, but probably there is a smaller decline even past 250k.

Re: OpenAI reduces Codex Model Context Size from 372k to 272k

#179

Post by BoorishBears »

skybrian wrote: post #37
tekacs wrote: post #26

I know a lot of people like to say that compaction makes this moot, but the level of detail you lose across compaction is wildly too much for most things that I do, unfortunately. Perhaps if your plans don't have as much detail, or if you're not, for example, having a discussion with a lot of nitty-gritty then it's fine? The lack of long context is the main reason that I still end up using Anthropic. The worst is whe…

That seems quite different from my design process. I write a plan.md that goes through multiple revisions. The plan is the memory. Restarting and reading the plan again to do another review is a good way to get a different perspective.

I've found if you pay close attention, models in Codex get briefly lost on where it is in the plan post-compaction. If it was in the middle of a test it often tries to resume the test from the start, or will seem "surprised" that past steps are completed already.

It's hard to believe that sort of confusion doesn't hurt performance a bit, the question is if that degradation is worse than the performance fall off from long-context (which is highly task specific)

Post reply on HN