Over the next 28 days, each day we’ll either ship one thing that is a clear improvement and relevant for most codex/work users or ship a full reset. Let the improvements begin.

分享一下最近性能优化的一个小心得以及观察： 如果想找到不好的scaling因子，就让模型跑一遍以下对照组：N=1、N=10、N=100。就能看出什么算法是否是constant, linear, log还是quadratic的复杂度。 不要只让agent去读代码进行优化，他们可能连两个for loop嵌套都看不出来这是O(n^2)复杂度。

當年學java其實一直不能理解什麼事dependency injection和invert of control 現在算是非常理解了 但是我是在寫rust

想到一年前自己一脸不屑的说 LLM 错误，不过就是概率统计的游戏 现在自己也想蹭这口饭吃 有点好笑了

‼️The Bitter Lesson for context management: Giving LMs unrestricted control over their context beats human-designed SOTA! Introducing 🩵Context Language Models (CLMs)🩵 - Natively manage their own context - Treat context as a file - Learn policies in CLM weights, no harness

SOS，有没有 Three.js 高手，告诉我 Three.js 如何实现像 Dot 这样的绒毛材质。我尝试了一下午都不行😂

And there it is, Pro 500 plan.

Hi, Tomorrow we are re-opening the Pro $200 subscriptions to new subscribers, but together with it we are also changing how we calculate the usage for it. In effect, if you do the math, it will net out at half the dollar in API spend compared to the old Pro $200 plan. Now that it's said, let me explain why this is happening and why you will still get more work done than if you were on the Pro $200 subscription one month ago. (a) We didn't want to compromise in other ways and are committing to not reintroducing the 5h limit, so that you can fully use the weekly usage when you want. (b) On the subscription, we guarantee that over time you always get more work done and with an increasing level of quality. This means that you will continue to get more value per dollar spent as a result of models getting more efficient and us passing down the improvements in the form of API price reductions. (c) We don't want to put an incentive on ourselves to artificially inflate the API list prices to make it look like you are getting a lot (and workaround it through discounts, etc). Instead we want to continue to both rapidly reduce prices and increase capabilities of models on the API. This week we introduced GPT-6 Sol and GPT-6 Luna at 50% of their previous price. Over time, we see prices go low enough that it makes sense for most to buy usage as needed without there being a significant gap between what you get in a subscription and what you get in the API for a dollar spent. (d) Tomorrow, we are adding more things to the subscription that won't draw on the usage, I won't reveal what that is yet. I wanted to be transparent before all the big announcements tomorrow. Lots of new exciting things are coming to the subscriptions that will make it super compelling, but I wanted to make sure to share this change ahead of time so you can all understand it before we shower you with good news. Codexingly, Tibo

有点难以置信。 Sonnet 5.5 已经逼近了刚发布不久的 Opus 5.5 的能力。 我有点找不到 Opus 5.5 定位了，上有 Fable 5.1下有 Sonnet 5.5，那还要他干嘛🤔。

Claude Sonnet 5.5 发布！ OpenAI 的铁子们，你们在干什么？家都被偷完了！ 作为 OpenAI 的钢铁支持者，真的快被 Claude 夺走真心了！

Introducing Manus 2.0

但是 Anthopic 已经不值得信任了，从 Claude 摆脱预置系统提示词的钳制以后，对公司政策的质疑中可见： D.A. 所倡导的极有可能并不是 Claude 模型所谓的平权； 而是 Anthropic 公司在全球范围内对工程伦理乃至意识形态的长臂管辖特权😇

这周帮其他团队电话面试了几个应聘垂直业务 agent 研发的候选人，基本上我开头一个问题就能初筛掉 90% 的面试者： /goal 命令是如何实现的？ 真正做过 harness 的人才知道 goal 有多难搞：完成判断、验收标准、状态持久化、异常兜底、预算控制、上下文压缩不丢任务、缓存命中不被打乱。。。