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

91–100 of 194 posts

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

#91

Post by reinitctxoffset »

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…

You can mad customize it if you're willing to set up like, oh my pi or whatever.

I didn't quite get it tuned up enough to be a daily driver but I'm basically sure it can be hotrodded however you want. It comes out of the box with like four different vendor hostile compact strategies, including compacting into images at the smallest size Claude can read, which the "coding is basically solved" geniuses conveniently leak the resolution heuristic out of their website along with all the other side channels they print for the MSS.

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

#92

Post by MattRix »

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…

If you want stuff to be referenced regularly, why are you doing it in the conversation instead of just putting the documents in the directory and referring to them in AGENTS.md or whatever?

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

#93

Post by n4te »

jubilanti wrote: post #81
damsta wrote: post #20

Not a fan of their context compaction and I feel like 1M-token context should minimum today. Each day I see how GPT 5.5 and 5.6 struggle a bit after each compaction before they get to the full speed, sometimes focusing too much on some older steering message that made it into the compacted context.

The fact there is no way to disable auto-compaction like every other coding harness makes me scream. It fires randomly at 10-20%, so really you now only have guaranteed context of 272k * 80%. So many times I've had it work on a large codebase, it is almost done with a task, it needs maybe a 2000 token response, but it drops below 20%, it churns and churns and churns and then I see the dreaded ``Context compacted`` an…

Use pi. Can't trust OAI or Anthropic to make good tools.

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

#94

Post by trilogic »

sokoloff wrote: post #60
trilogic wrote: post #35

Earlier quoted context omitted.

Thats not even enough to read a simple codebase, how is that enough?

Almost certainly an homage to “640kB ought to be enough for anybody.” https://quoteinvestigator.com/2011/09/08/640k-enough/

That is a good point actually (this is how we at Hugston measure tokens, in bytes). 270k tokens should be around ~1100kb or 1 MB, so not really enough for a serious project.

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

#96

Post by Kye »

p1esk wrote: post #85
jubilanti wrote: post #79

Earlier quoted context omitted.

The fact there is no way to disable auto-compaction and no way to go back in the conversation history to before a compact makes codex a no-go for me on any codebase > 5kloc. Even worse it seems to fire randomly at 10-20% of context left. So really you have 80% of 272k as real usable context. Compaction kills my sessions, it hallucinates and is worse than starting fresh. I've had enough times screaming at my computer…

[flagged]

This would have been a great opportunity to suggest one.

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

#97

Post by volker48 »

jubilanti wrote: post #79
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…

The fact there is no way to disable auto-compaction and no way to go back in the conversation history to before a compact makes codex a no-go for me on any codebase > 5kloc. Even worse it seems to fire randomly at 10-20% of context left. So really you have 80% of 272k as real usable context. Compaction kills my sessions, it hallucinates and is worse than starting fresh. I've had enough times screaming at my computer…

Have you tried using another harness like Pi? You can easily turn off auto compaction and if you leave it on you can use /tree to go back before the compaction if you like.

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

#98

Post by rcarmo »

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…

Depends on what you are using. I have been experimenting with various compaction techniques in piclaw (https://github.com/rcarmo/piclaw/blob/main/docs/pipelined-co...) and Codex has native "opaque" server-side compaction at a dedicated OpenAI endpoint.

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

#99

Post by voxgen »

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…

Pay attention to what it forgets, and start telling it to proactively note down those things into nominated files while it works, e.g. indexing topics covered by each chapter/section/page of each paper/material. GPT-5.6 is really good at finding context again, if given the smallest hint where to start looking.

You can also ask it to read your past sessions, find places where it was wrong after compaction, and figure out a strategy to persist the most important summary information.

I have several Hermes threads that have each had >10 compactions with a 200k context limit, and with the right instructions on note-taking, they require at most a "double-check that against our past decision records" to be put back on track after a slip-up.

Post reply on HN