Ricko Yu (@cosmtrek) header
Ricko Yu (@cosmtrek) profile picture

本账号屏蔽营销号,追求有趣的活人感,致力于长期探索人和 AI 协作机制

Joined December 2013
这个视频后面的话题非常好,当执行资源充裕乃至冗余之后,组织会有哪些变化? - 企业需要明确做什么,界定目标和意图对齐 - 拥有清晰的审美和说不的判断力 - 中层管理大幅削减,诞生更多的 DRI 角色,统筹 AI 智能体,直接对结果负责
At @SpaceXSI, Lauren Tan (@poteto) and Roman Ugarte (@romanugarte_) are on the core team that took Grok Bot from first line of code to launch in seven weeks. It lets you spin up AI teammates with their own identities and logins, and they just keep working in the background. Their marketing team gave a bot its own ad budget. Lauren built an entire feature with her bot in one Slack thread without ever opening Cursor. They joined us on the @LightconePod to talk about what it’s actually like working next to bots every day, and how the hard part is shifting from doing the work to figuring out what to do and why. 03:36 — Giving Bots Real Jobs 06:49 — One Bot or a Team of Specialists 10:39 — Sharing Bots Across the Company 14:46 — Identity and Permissions for AI Coworkers 18:37 — Bot-to-Bot Collaboration and Trust 22:35 — The Workflow Behind 4,000 PRs a Month 26:00 — Teaching Agents to Write Code You Trust 29:01 — Building a Personal Software Factory 33:44 — The Future of AI Coworkers 36:47 — Rethinking the AI-Native Company 40:13 — Teaching Agents to Check Their Own Work 43:56 — How Much Code Review Is Enough? 47:33 — Codebase Guardrails That Save Tokens 52:20 — When Product Judgment Becomes the Bottleneck 56:29 — From Finance to AI Engineering
176
周末来湖州打两天红土,刚举办过 WTA125 赛事,场地很顶级
2
1
260
上午又打了一个小时
97
没有完美的 agent 编排产品,与其浪费时间去持续寻找,不如找个自己认可的项目,fork 出来改造成自己喜欢的模样 Keep building
128
Google 也发布了决策模型 Decision,已用在 grok bot 工作流里,应该能省一些 bot 用量
1
1
201
We're introducing the Gemini Decisions API in @GoogleAIStudio, powered by our new Gemini Decision 1 model. Instead of generating a text response token by token, Gemini Decision 1 evaluates your input (across text, images, audio, video, and PDFs) against up to 1,000 questions to make fast, confident decisions in a single pass, with zero output tokens billed. Here's a look at how it works 🧵
78
两年前订阅 AI 产品 20 刀嫌贵,现在感觉 100 刀才是标配
1
172
Gemini 4 Carbon medium 有点慢呢,效果上看着不错
1
219
我的一台开发机上的模型输出速率,opus 很强,而 carbon 慢一半左右。。。
1
159
Claude 又给了一次额度重置机会,临近 IPO 态度就是不一样🫡
We've given all Pro, Max, Ultra, and Team users one free full reset, across all models and limits. Use it anytime before December 10 at 2:00PM PT. We recently fixed a few small issues that used more limits than intended, and the Fable resets didn't do much for those of you who'd already hit your weekly limits for all models. While these issues didn't affect everyone, we want to make up for the trouble. You'll find it in Settings > Usage, or at clau.de/reset.
1
211
最近在优化自己的工作流,每周五晚上跑分析任务,分析本周的 claude 和 codex 会话,找到可提升的地方,可复用的经验沉淀为技能、工具或者脚本,缺上下文的则补充进笔记里,这样可以持续优化 agent 执行效率。 我的职责在逐渐转变成构建环境和完善上下文😂
11
13
79
6,305
相比 tstack、mcode-stack 和 pstack 里的对应方案,上面这个工作流更有优势
53
清理了一半的 bot,把这些 bot 转化成技能教给 Chief 来掌握😂
216
给 Claude Code 写了个委派任务技能,分工很简单:Codex 负责「看清楚」,Claude 负责「想清楚」,实现只在想清楚之后才派出去。
5
3
25
3,372
为什么这么分 统计下来,主会话约 80% 的开销是缓存读,上下文越长越贵。把翻代码、查日志这些移出主会话,比省输出 token 有用得多。 技能持续优化 每次派发自动记台账,复核后补上结论和失败原因。定期复盘,把学到的写回技能,具体事例留在复盘记录里,技能正文只写原则。
285
Claude Pro 也能体验 Fable 5.2 了🫡
180
中午去洗牙,顺便补了两颗牙,一共花了六百多。 因为以前长期横着刷牙,牙根磨出了楔状缺损,今天先把最严重的两颗补上了。以后刷牙真的要注意姿势。
1
450
有时候觉得时代发展太快,年初没多少人相信交给完全 AI 写代码,现在年底已经没多少人会手写代码,我能手写代码全凭练出来的肌肉记忆😂 当然,想想 Transformer 论文是 2017 年发布的,至今快十年了,这么看一个行业的更新也是需要非常长的时间积累,才能在最后时刻完成质变。
1
5
598
自从 grokbot 大砍之后我都不随便聊天了,30 刀的订阅性价比极低极低,怀疑 @elonmusk 是不是不想做这块业务了。 我现在的解决方案是把 grokbot 定位成最轻量的人机交互层,迁移固定的任务下沉到 claude 和 codex 里,再归并一些不重要的 bot 到 chief bot 里。
2
283