ferstar retweeted
Over the past week, I’ve been overwhelmed by the love and support of friends, industry colleagues, and people I've never met. Thank you to everyone who has shown kindness to my family and me. It means the world to me.
I came to the United States 53 years ago, and becoming an American citizen is one of the greatest gifts and proudest moments of my life. NVIDIA has been my life’s work. Building it into the company it is today alongside my colleagues has been a privilege and an honor. Nowhere but in America could a company like NVIDIA be possible. I love our country, and I love NVIDIA.
I did not live up to the standards expected of everyone at NVIDIA, and I have made serious mistakes in my personal life. I created problems for the Board that I deeply regret. I own my mistakes completely, and I am committed to cooperating with the Board’s independent investigation.
Since my departure, I’ve seen an outpouring of calls from NVIDIA’s employees, investors, business partners, and customers for me to return as CEO. Many continue to reach out to me directly as the company navigates complex technology, market, competitive, and geopolitical dynamics. NVIDIA is a once-in-a-generation company. If the Board of Directors decides that my return is in the best interest of our shareholders, our employees, the company, and America, I would be honored to answer these calls and return as CEO.
Thank you again to everyone who has shared their good wishes. I am profoundly humbled by your support. To my family: I love you, and I will spend the rest of my life being worthy of yours.
Jensen
ferstar retweeted
Introducing cc-remote.
Claude Code eats your RAM and CPU. But why run the harness locally?
cc-remote runs the harness in the cloud, while keeping tool execution local.
Run 10+ Claude Code instances on a 16GB MacBook Air.
别被两台 DGX Spark 的跑分视频忽悠了。
拿 QSFP 铜缆直连拉起 MiMo-V2.6-Flash(TP=2):
- 测 128 token 短 Prompt:6 并发总吞吐能冲到 173 tok/s,看着很猛。
- 挂进日常 Coding Agent 真实上工:起 5 个子 Agent 扫项目,单路直接暴跌到 15–25 tok/s,6 分钟连一个子任务的结果都没吐完……
底层逻辑很赤裸:ConnectX-7 实际上只分到了 PCIe Gen5 x4(单向理论上限 126 Gb/s),更要命的是 LPDDR5X 统一内存带宽只有 273 GB/s(对比 4090 的 1008 GB/s)。
堆双机只解决了“显存能不能装下”,根本解决不了“单路解码就是慢”。除非你的代码隐私贼贵死贵,或者买来当桌面大玩具刷跑分,否则别指望它带飞多 Agent。
完整实测数据与真实避坑分析:
blog.ferstar.org/posts/dgx-s…
#DGXSpark #LLM #CodingAgent #AIInference #NVIDIA
ferstar retweeted
Replying to @affe_is_me
果断关掉compact,剩百分之十的时候就果断新开thread,旧thread用memory工具保存,然后告诉新thread从保存的位置按需读取信息。推荐一个大佬的工具 @wey_gu
ferstar retweeted
现在每天大概会 Compact 30多次 Claude Code, 每次 Compact 后都会丢失一些信息;
如果从文件里读 Context 也会遇到很多问题, 譬如每次读和写的 Tool Calling 也会消耗 Context Window.
大家有无什么推荐的最佳实践呀呜呜呜
ferstar retweeted
CF 真是一个超级认真又迭代迅速的公司,这篇博客抽丝剥茧的分析了 Cloudflare workers 的性能问题,和 Vercel 有差距的原因,最后提出改进方案。
blog.cloudflare.com/unpackin…
每次有问题以后它们的文章都堪称透明准确,从来不会掩饰问题,非常认真的说明原因和解决方案。强烈建议大家读读看,还能学到很多云服务实现的细节。
想起之前国内一些云的事故,遮遮掩掩,从来都是永远不知道原因和怎样解决的。甚至 status 都是假的,服务都挂了还挂着 “All Systems Operational”
Cloudflare investigated CPU performance benchmark results for Workers, uncovering and fixing issues, making Cloudflare Workers faster for all customers.
blog.cloudflare.com/unpackin…
ferstar retweeted
Replying to @dotey
黑猫白猫,抓住老鼠就是好猫。能陪着产品活下来的代码,无论 AI 还是灵魂手撸,都是好资产。代码里面冗余,注释其实无所谓,但测试都开始胡写乱 mock,这不应该反思人的问题么?明明是软件工程管理的锅,为啥要甩给 AI?
ferstar retweeted
1) World Mobile is a new global 🌍 mobile network based on the #SharingEconomy.
Our #MeshNetwork is built and managed by the people, for the people, using #RenewableEnergy and #Blockchain. $WMT
TG: t.me/WorldMobileTeam
A thread 👇
ferstar retweeted
I believe person to person transmission exists, but Chinese people are now trying their best to fight for it and control it within China. If we are out of China, be cautious, be careful, but no need to be panic














