Looks like we will be waiting quite a while to see a 1M context window from OpenAI
OpenAI reduces Codex Model Context Size from 372k to 272k
41–50 of 194 posts
Re: OpenAI reduces Codex Model Context Size from 372k to 272k
#42claudes/codex performance suffers after 250k anyway and my workflow reset after every 200 so this is a non-issue
Re: OpenAI reduces Codex Model Context Size from 372k to 272k
#43I 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…
I agree. Compaction sucks, so I made tools that let the LLM selectively delete (and recall if needed) chunks of its context. You might want to try context bonsai if you're routinely hitting the auto-compaction wall. https://github.com/Vibecodelicious/context-bonsai-agents
This is actually brilliant. I've seen other approaches where the context is selectively pruned, but never in a recoverable way.
P.S. Love the "bonsai" name btw!
Re: OpenAI reduces Codex Model Context Size from 372k to 272k
#44Earlier quoted context omitted.
I agree. Compaction sucks, so I made tools that let the LLM selectively delete (and recall if needed) chunks of its context. You might want to try context bonsai if you're routinely hitting the auto-compaction wall. https://github.com/Vibecodelicious/context-bonsai-agents
I have a hunch that OpenAIs proprietary compaction endpoint actually does something similar on the backend.
When I've asked Codex agents about things that were in their context window, they've never – to my experience – been able to actually retrieve something from before compaction when using the proprietary compaction endpoint. Instead, they've had to consult their actual transcript.
So... at least as of a week ago or so, I don't believe so.
Re: OpenAI reduces Codex Model Context Size from 372k to 272k
#45Re: OpenAI reduces Codex Model Context Size from 372k to 272k
#46I 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…
What plan are you on? With Anthropic I run out of quota very fast on a Pro plan with long contexts. Is long context primarily for Max tier or for API usage? Or are there special ways of working with long context on a Pro plan?
Yep, Max. I would definitely struggle to code with Anthropic's plans on Pro.
Re: OpenAI reduces Codex Model Context Size from 372k to 272k
#47I 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 best way around this for me is planning a project well ahead of time and using subagents to execute individual tasks while the primary agent acts as a PM.
That isn't really a way around it for the kinds of things I'm talking about. The whole point is that getting all of the relevant context to even orchestrate it takes up most of the model's 272K.
Re: OpenAI reduces Codex Model Context Size from 372k to 272k
#48I 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 have these plan files as well, but it depends on the scope and scale of the things you're executing on, I think. However much detail gets put into the plan, it still doesn't help if part of what the model needs to understand is the fine-grained / perfect detail of a large surface area.
Re: OpenAI reduces Codex Model Context Size from 372k to 272k
#49Does the context size really matter that much if a “dumb zone” starts around 120k-150k anyway?
Re: OpenAI reduces Codex Model Context Size from 372k to 272k
#505.6 is a mess