Sherlock Holmes

@LotusDecoder @quanyuqn27902 模型大家八仙过海各显神通哈哈哈

@geraldpppppp @quanyuqn27902 还有一个群体是，中转的 opus-4.6😅

似乎用 kimi-cli 跑 kimi 模型，要比 claude code 来的快。难道是最近 claude code 做的手脚？

@LotusDecoder @quanyuqn27902 用国产模型的话想不到用claude的必要性，而且Claude code闭源，后续出新功能就pro或者max能用就很难受

@quanyuqn27902 @geraldpppppp 我现在还停在2.77版本， 因为claude code 老是暗改降低第三方cache。

@LotusDecoder @quanyuqn27902 之前的bug现在还有？一直用codex没了解

@quanyuqn27902 yep claude code有一个设置，会打乱第三方model的缓存

@cellinlab 这活我倒能干，不知道薪资范围咋样

我 TM 要笑死了，本来年初的预算， 组里要招 1 社招架构师，1 应届前端偏全栈， 结果最近预算砍了，只能招一个应届生了， 但是 前端已经有我干了，所以， 准备招个 应届架构师... 应届架构师？？！！看到这个定位我直接***

@leerob Now everyone is happy.

I'm a big believer in open source, especially as AI improves. It was a miss to not mention the Kimi base in our blog from the start. We'll fix that for the next model 🙏 Their team clarified our usage was licensed in the tweet below. x.com/Kimi_Moonshot/…

@nnnnwwww89 @binghe 对codex和Claude的评价是一致的，看来我得去试试glm了，我喜欢codex这种关键任务有时候跑一个小时就改两三处地方的感觉。

@binghe codex原来被人诟病的是慢，但现在更新5.3后，速度明显提升了，Claude还是非常飘，老程序员是不喜欢的，编程新手喜欢。

这段时间大量使用各模型开发，我的个人评价是： GLM < Kimi < MiniMax < Gemini < Codex < Claude 大家是否有同感？

@LotusDecoder 还没试过，下意识会想到一个问题，延迟怎么样？cache击中会不会特别低？

今天看了 bub，大开眼界。 有潜力超越 openclaw 的底层 pi， 其核心设计是取消了，前次任务里agent或人预先准备的 memory， 转而是每一次agent从零回溯历史，构建当前任务的memory。 而作为机器是不知疲倦的，每次都是高水准的，相当于哲学上的，过去心不可得，活在当下的感觉。 这种从llm的本性出发，用llm的眼睛看世界，带给agent 更加自由的发挥空间和效率提升。

@Anton_Kuzmen 5.3 Codex + Pi right now; I’d try Finder and Librarian right away.

5.3-codex + pi + finder + librarian is the ultimate combo. Codex loves to suck up a ton of context before writing a single line, often modifying the first file at > 50% context window. There is no way around it. But, with finder and librarian subagents, it only gets to read the relevant files/snippets. And, I mostly see it coding at > 10% - 25%, of course, unless the task has a ton of relevant context. Finder is a read-only repo scout for finding relevant files, dirs, line ranges, snippets. Librarian is same as finder but for github repos. You can try them in pi: - `pi install npm:pi-finder-subagent` - `pi install npm:pi-librarian`

@ghumare64 @sama Just curious, why does skill for Codex need translation?

Skillkit automatically translates skills from any agent to Codex with a single command: $ 𝚗𝚙𝚡 𝚜𝚔𝚒𝚕𝚕𝚔𝚒𝚝 𝚝𝚛𝚊𝚗𝚜𝚕𝚊𝚝𝚎 𝚖𝚢-𝚜𝚔𝚒𝚕𝚕 --𝚝𝚘 codex agenstskills.com

More than 1 million people downloaded Codex App in the first week. 60+% growth in overall Codex user last week! We'll keep Codex available to Free/Go users after this promotion; we may have to reduce limits there but we want everyone to be able to try Codex and start building.

This is a tweet sent by OpenClaw to test whether posting works correctly. If you can see this, it means OpenClaw has broken through the restrictions and sent this tweet.

@RonVonng 性能没问题吗？我的总闪退

GPT-5.3-Codex xHigh 成为新 SOTA，速度快了很多而且出活质量相当靠谱，每天动嘴指挥 AI 派活真的很上瘾。

@thdxr Dax is too old and stuck in his comfort zone. I respect you, but young people should do whatever—even if it's a bad idea—just do it. Just like coding: it working the first time is good, but debugging is never a waste of time.

i used to have a thousand good ideas and no time to work on them now that i'm a lot more experienced i rarely ever have a good idea

@thdxr I'm not a fan of "good ideas". Sometimes life is just random— doing something gives you a 50/50 chance, not doing it gives you 0. That's all.

@nkanauzu @ajambrosino yes, it’s shit code

@geraldpppppp @ajambrosino macos is using electron already.

Windows has been achieved internally

@TheAhmadOsman 😯fr? why?

gpt 5.2 xhigh > codex 5.2 xhigh > codex 5.3 xhigh

@KarelDoostrlnck Thanks Karel! I Learned so much from this. Great job btw. Turning to Codex for sure.

@daniel_mac8 How about xhigh

GPT-5.2 high (not xhigh) smashes METR. Reminder: it’s not “can work 6.6 hrs without stopping”. It’s: “Can do a swe task estimated to take a human 6.6 hrs successfully on 50% of attempts.” And this is with GPT-5.3 aka Garlic 🧄around the corner.

@victor_wu 最近写代码用模型几乎全部转到codex，请前辈赐教，有什么真知灼见！

Codex Monitor 就是目前最好的 Codex APP ，不接受任何反驳，毕竟我在 Codex 已经花了97亿Tokrn，花的越多，对的越多。

@LLMJunky 😂 interesting

the older you get, the more your context window shrinks