Papain Tea🎋

[Papain Tea🎋 @Papain_Tea]

Let’s see what Tibo said before.
https://t.co/xcsE3vWBxS

[Tibo @thsottiaux]

For clarity, while both are called 20X, in Codex they apply specifically to weekly usage limits. And we also don't have 5h limits for both Pro plans.

The Pro 20X is quite precisely 20X the usage of the Plus subscription, so it does exactly what it says on the tin.

[Papain Tea🎋 @Papain_Tea]

@CY160909 @ChrisGPT Absolutely Claude.

[Papain Tea🎋 @Papain_Tea]

@cactuscompute Can you support Chinese？

[Papain Tea🎋 @Papain_Tea]

@AlexFinn why not batter than GLM 5.3？

[Papain Tea🎋 @Papain_Tea]

When is Codex going to offer a 1M context window for free, like Claude does?

258K is simply not enough for serious coding work. It fills up ridiculously fast on any moderately large project, and then you’re forced into compaction over and over again.

And the worst part is that the compaction isn’t even good. It throws away way too much important context—implementation details, previous decisions, constraints, debugging history—and the model starts forgetting things it absolutely should know.

A coding agent is supposed to work across large, long-running codebases. Context shouldn’t be the bottleneck.

Please give Codex a proper 1M context window without charging 2x for it. 258K + lossy compaction is not a serious long-term solution.

[Andrej Karpathy @karpathy]

Cool eval. Simply ask an LLM “Land or Water?” and give it a latitude and longitude coordinate as text. Ask 16,200 times, plot as image. The models know. From compressing the internet.

[DAN KOE @thedankoe]

https://t.co/7l7Jef99QZ

[Papain Tea🎋 @Papain_Tea]

@olive_trees234 @akazwz_ 我发现api支持，我用的都是oauth的codex，抱歉

[Papain Tea🎋 @Papain_Tea]

@olive_trees234 @akazwz_ 5.5就不是1M模型

[Papain Tea🎋 @Papain_Tea]

@hylarucoder 其实还蛮有用的，利好我这种使用时间不均衡的人，这两天用下来都没有达到过五小时上限

[Papain Tea🎋 @Papain_Tea]

@sdlfj10 @dotey mac可以

[Papain Tea🎋 @Papain_Tea]

@dotey 这玩意用着好慢啊

[Papain Tea🎋 @Papain_Tea]

@ollama @lemonkillergame 还有中文客服啊（）

[Papain Tea🎋 @Papain_Tea]

@ClaudeDevs 能提高提高每週的限度嗎

[Papain Tea🎋 @Papain_Tea]

is there any great harness framework for deepseek？

[Papain Tea🎋 @Papain_Tea]

@dotey huashu的那个design怎么样？