meta的muse 还有grok 的 bot 一些新的agent产品 我是真的没兴趣碰 本质都是一个Loop 也就是ReAct的实现： while True: thought = llm(context) action = parse(thought) result = call(action) context += result 再套上不同的壳，这就是Agent

中转站能有什么信誉，两家都是

如果你觉得你的压力很大，不妨想想明天的 Tibo，他要发布多少东西，才能让你觉得 Codex 砍一半额度是值得的

👀 TIL about W3C WebSkills - Agent Skills, stored in the browser - Running scripts in a Web Worker - navigator.webskill API - Completes WebMCP / On-Device LLM Recently pitched by a Huawei contributor at a W3C seminar Interest in incubating the project webskill.ai

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

本文没有 aff。 之前买了 Opencode Go 用开源模型（比如 ds），十刀一个月也算是量大管饱了，不过最近发现 Command Code 也出了类似的套餐叫 GOAT，主打折扣后的开源模型。 Command Code 可能大家不知道，之前是做 taste 系列模型的，会在每次 apply 代码的时候学习你的偏好，这算是他家最大的差异化卖点了，也算是记忆系统之外的一个选择，在当时比较超前。 最近他们拿了融资，产品的 agent 能力也慢慢追上了，该有的功能都有，比较有意思的是自带了一套涵盖网页设计、代码评审的工作流，算是直接喂到嘴里了。 迁移起来基本没什么难度，支持 skill mcp 是当然的，UI 也比较接近 Claude Code，支持直接从其他 agent 里学习，冷启动成本蛮低的，而且也支持国内的支付方式，对国人还是比较友好的。 这几天可能会继续更新体验 command code 的感想。

Also launching today, and this is the big one: cf in open beta. cf is the new CLI for the whole of Cloudflare. Where Wrangler focused on Workers, cf exposes the whole API surface for agents. Testing this has made using Cloudflare so easy. blog.cloudflare.com/cloudfla…