Yoyfun

目前微信claw bot只能同时绑定一个openclaw或者其他agent。理论上可以复制配置文件出来其他agent cli里面使用？想了下这种多环境接入封号概率可能上升，而且不方便管理。所以我做了个hub，这样后续可以通过“网关”来接入多个agent。目前还加入了原生的llm对话和webhook接入。github.com/youfun/WeClaw-…

@wayen_ai grok 30刀订阅额度不多

周一一天就给我一半干没了? 这 grok4.5 这么耗额度的吗

@historianseldon @skiffprivacy SpaceX AI should delete all uploaded data, regardless of whether the user requests /privacy or not.

@milichab @skiffprivacy thats great but what about us plebs who arent enterprise customers? privacy options aren't available for non enterprise customers. this is shady af and why i'm never switching from codex.

I worked on building an end-to-end encrypted email/docs/files/calendar app @skiffprivacy for 4 years and care deeply about privacy. ZDR and /privacy are always respected in Grok Build - and swapping your setting with /privacy deletes any synced data retoractively

@elonmusk SpaceX AI should delete all uploaded data, regardless of whether the user requests /privacy or not.

True. As a precautionary measure, all user data that was uploaded to SpaceXAI before now will be completely and utterly deleted. Zero anything whatsoever will remain.

@syhily 如果是llm相关的书，就国内出版效率来说。出版了就已经成为网络上能搜索到的信息。好处想是省了搜索时间

内容基本上都是常识，后悔买了……

还可以用gork订阅。不错不错

@plantegg 做数据库的大佬

这位大佬大家认识吗？一直自己研发，上班很少。现在40多岁了，突然想去上班了。可能是在医院被人家叫叔叔刺激到了。

@aronhouyu 三个月内产品迭代43次。其实还好。我手头一个项目 1天一个版本。1个月就30个版本了 。要看都更新了什么。而且腾讯应该不限制token消耗。对他们来说要把迭代版本数量搞上去不是问题

workbuddy 日活1300万 月活2000万 牛逼的营销能力 三个月内产品迭代43次 skill库79万个 办公agent的天花板 但是我从来没用过workbuddy

让codex cluadecode pi agent之类帮忙网站运维要关注一个问题：这个agent有没有读取你的密钥或者env。上次让pi 排查一个问题。直接读取我的env。后续只能把数据库密码换了重新部署。浪费时间。如果没有关注到他读取到了env。那么这个env里面的密钥/密码之类的存在泄露风险

@feltanimalworld 的确恶心

非常疑惑：大量蓝V留下明显AI生成的评论。为啥？图啥？

新一代人类，在某个阶段之后应该不能在末日时代手搓代码了。这个时候如果一个人能手搓代码，便会成为很重要的资源。因为末日时代。因为能力+资源紧缺。算力很能被找到和使用。想象一下你作为一个会手搓代码的工程师穿越到这个时代能发挥到作用。当然也可能是彻底末日时代。连计算机都用不了了

@LyonShrimp @fiapp_pro 前几天上的周额度限制

@fiapp_pro 它不是月额度吗？哪来的周额度？

grok cli + cursor composer 2.5 有点爽的过头了， 高强度使用半天，周额度才用 3%， 写大部分的项目都能够胜任， 并且因为 cursor 用了自己的数据后训练，你能感觉到是一个工程师在跟你交互，而不是一个大聪明套小聪明。 唯一的问题就是不能当许愿机，模型在其他领域的智商还达不到，如果你本来就是程序员，你会很喜欢。

@liber2theword @mizorewww 比cursor的还多？

@mizorewww 目前glm5.2最低价渠道了

试了一下ollama 20刀的版本 说实话额度不咋多，但3h限额给的感觉可以和GPT 20x媲美了

llm受害者+1。让他帮我移动目录。搞没了

@wadezone 微信还信用卡也是要手续费的。或者搞几个腾讯联名信用卡 可以免一些手续费

还是评论区出人才

@Bart_Blast cool cool cool

Soon I start building the most ambitious thing I've attempted with Hologram (my full-stack Elixir framework): the Local-First data layer. Your app keeps its data locally, syncs in the background, and keeps working offline - all of it written in Elixir. Ambitious enough that before writing any code, I spent the past months studying every serious sync engine out there - Electric, Zero, Automerge, Jazz and friends. I came out with a pile of notes and a few opinions I didn't expect to have. Some of it made it into my ElixirConf EU talk this year - I'll share the video here once it's out. (And the regular releases keep coming while I work on this - v0.10 went out this week, about a month after v0.9.) So I'm turning the research into a landscape analysis blog post. Before I write it - what would you want it to answer? How the engines compare? Where they fall short? What any of this means for Elixir?

@FGLXLucas 有人说gork 300刀订阅大约价值50刀 这个的确太少了

xAI’s Grok Limits: Transparency Deficit and Strategic Risk in a Brutal AI Market In recent months, xAI has repeatedly adjusted SuperGrok usage conditions without clear communication. Instead of fixed, contractually guaranteed render and usage capacities, there is now a dynamic weekly shared budget that is quickly exhausted, especially for compute-intensive features like Grok Imagine (images and videos). Users like Luc report that even with efficient usage (e.g., one 30-second film plus two 10-second clips per day), the budget has become noticeably tighter — a development many perceive as yet another 50-70% reduction. The problem goes far beyond casual users. Developers using Grok for complex programming, agent workflows, or long-running analyses are equally affected, as are creators who generate income with the outputs. This becomes particularly critical for future applications such as robotics (Optimus) and mobile AI, where reliable compute planning is essential. Anyone who builds their workflow or even their business model on Grok risks sudden restrictions or hidden upsells (Heavy tier, extra credits). For xAI, this is a risky game. In an extremely competitive AI market where OpenAI, Anthropic, Google, and specialized providers are fighting for developers and companies, trust and predictability are key differentiators. Frequent, opaque limit adjustments create exactly the kind of dependency that can later lead to higher prices or churn. Many professional users are already consciously diversifying and using Grok only for quick tests, while relying on more transparent alternatives for productive work. Conclusion xAI has excited many users with Grok and SuperGrok — but the current limit policy undermines precisely the trust needed for long-term success in the AI industry. For users, this means: diversification and critical review of dependencies are advisable. For xAI: greater transparency and reliable capacities would be a clear competitive advantage rather than a risk. #Grok #SuperGrok #xAI #GrokLimits #AILimits #AITransparency #xAICriticism #GrokImagine #AI #ArtificialIntelligence #TechBusiness #xAIRisks

@liustack 有些项目其实不需要pg数据库，上sqlite就行，有些项目甚至不需要sqlite

看见下面很多人在表达没有 sqlite 你这个干不了那个干不了，我就想笑。现在的程序员啊，离开数据库已经不会写代码了，根本没人去关心底层存储系统了。但凡你了解过磁盘原理，了解过怎么实现 kv 存储系统，了解过什么是 newsql，你都会对 sql 存储引擎或者说 db 祛魅。很单机场景的很多功能实现，写文件就是最优解，没有之一。不是说 sqlite 不好，是不需要存复杂关系你就不该上数据库

@chenbimo 挺好。我现在是写脚本打包部署的。考虑加上版本备份回滚机制么

@cnzhihao @dearemon

@dearemon 后续呢？截图要截全啊

做一个最近72小时代码变更review ，使用amp code +glm5.2 的tolen消耗和费用