Leechael (@Leechael) header
Leechael (@Leechael) profile picture

Build confidential computing at @PhalaNetwork Spend the rest of my time making AI agents & harness

Joined May 2007
Photo by Leechael (@Leechael)Photo by Leechael (@Leechael)Photo by Leechael (@Leechael)Photo by Leechael (@Leechael)Photo by Leechael (@Leechael)Photo by Leechael (@Leechael)Photo by Leechael (@Leechael)Photo by Leechael (@Leechael)Photo by Leechael (@Leechael)Photo by Leechael (@Leechael)
GEO 大会现场。我感觉下次去参加各种活动必须是要能面基一些人,不然没太大意义,净听广子了。 😅
2
171
OpenAI 为什么没证明出黎曼猜想呢? 因为内部模型证明完了之后补了一句:“需要强调的是,通过 Lean 形式化证明并不能说明 Lean 代码和论文数学表达一致”
34
43
13
1,594
121,452
Man, what a day
39
900
75
8,838
282,533
Opencode 又不能开发票。
This quoted post is unavailable.
112
很多人都 vibe coding 做了 markdown editor / viewer。然后我选择再买一份 byword;哪怕在很多年之前,我已经在国区买过一份。
138
希望明天 O/ 有 one more thing
假设你是 A\ 管理者,明天上市,今天 O/ 发布了最新的模型(并且你不知道水平如何),而你手头上还有未公开的模型(路演 slides 透露了?),那么上市当天的策略之一,是不是再发一个模型?
216
假设你是 A\ 管理者,明天上市,今天 O/ 发布了最新的模型(并且你不知道水平如何),而你手头上还有未公开的模型(路演 slides 透露了?),那么上市当天的策略之一,是不是再发一个模型?
1
1
356
当你做了一个服务,开始有一些用户量,也有一点余量人力看安全相关的事情,那么尽可能搞一波基于 agent 的 red team 模拟攻击,针对生产环境。
2
7
800
大概四天不到就用完一周的额度,还是 Ultra。还是选择便宜的套餐苟着吧。这个钱还不如扔 OpenCode Go 然后只用 Deepseek v4.1 flash。
不知道其他人有多少 token 用量比例是消耗在 routines 上的? 或者分析一下,看看消耗最大的 routines 是什么,怎么优化?
2
1
332
我觉得,从 GPT 6 开始就已经这样,6.2 只是更失控了。我甚至觉得还不如继续用 GPT 5.6。
145
哥,我很想说发邮件这个事情不是能随便 redesign 的……就是 UI 还不是这一类型服务的卡点。
我给自己打造了一个小型的 Resend 替代工具,虽然现在 UI 还很丑,但它能正常工作。 目前用它来为 Fog Mail 的付费用户发送 iOS TestFlight 邀请。
1
2
962
如果再出来一个好用的开源 personal agent,那么它的核心竞争力肯定是能稳定使用现有的 A\ 订阅。
突然想到一个事情。OpenClaw 突然火爆的时间点,其 aha moment 来自于 opus 4.6。而 Grok bot 则是 Opus 5.5。
3
289
突然想到一个事情。OpenClaw 突然火爆的时间点,其 aha moment 来自于 opus 4.6。而 Grok bot 则是 Opus 5.5。
2
1
6
1,365
antigravity 和 gemini 的这一波提升有点像是上一年哄骗我订阅、结果用上没到几个月就变💩、还要一整年下来基本用不了的几次。 所以我还是看看就好,有第三方 provider 再来尝鲜就好。
1
3
562
不知道其他人有多少 token 用量比例是消耗在 routines 上的? 或者分析一下,看看消耗最大的 routines 是什么,怎么优化?
1
488
I’ve decided to leave NVIDIA. There are a few things I want to say. As a robotics engineer at NVIDIA, I have seen Jensen as much more than the company’s CEO. I admire his willingness to invest in a future that was not yet obvious. He committed to CUDA long before the deep learning boom and positioned NVIDIA for AI before it became everyone’s priority. Those decisions helped build the infrastructure that powers today’s AI. I have seen that same vision in physical AI: investing in robotics, sharing open-source tools and projects, and building computing platforms that bring AI into the physical world. This is the work I do every day—and a future I believe in. But what matters most to me is the culture he helped build. Engineers are encouraged to explore, take risks, and learn from mistakes. Jensen reads employees’ Top 5 emails, follows their work, and engages directly. In a company this large, that connection matters. It makes an individual engineer feel that their ideas can still be heard. That is why this has been so disappointing. I do not have all the facts surrounding the allegations, and I cannot prejudge the investigation. My admiration for Jensen does not put him above scrutiny. What I find difficult to accept is having to come to terms with his departure before receiving an explanation that helps me understand it. What this means for our direction, our culture, and the people doing the work remains unclear to me. I have felt that engineers’ perspectives matter here. On this decision, I have not felt heard. That gap has been more painful than I expected. I understand that some information cannot be shared immediately. But that does not erase the feeling of being left outside a decision that affects the company we help build every day. A company’s greatness comes from its leadership, its governance, and the people who turn its ambitions into reality. Employees’ trust and sense of belonging are part of that, too. Jensen’s vision and the engineering culture he shaped were important reasons I wanted to stay. His departure led me to decide that my own chapter here should also come to a close. I leave with sadness and gratitude. The colleagues I have worked with, and the work we believed in together, will always matter to me. These are my personal views.
4,051
13,751
1,203
133,887
7,039,206
Leechael retweeted
In my spare time I've been jamming on my own orchestrator: a native SwiftUI Mac app built on pi-durable (of course!) I just talk to one "chief of staff" agent. It delegates async to an agent lead per project, each runs its own subagents, they all talk to each other, and only the decisions that need me land in my Inbox. Because it hands everything off, the chief is always free: I can keep piling on new tasks across projects mid-flight and it keeps them all moving in parallel. It renders in-chat gen UI built from real native Swift components, Mermaid diagrams via a native Swift port of Pele + rich HTML inline. Fun as hell to keep iterating! Thanks @badlogicgames 🫡
54
13
4
457
28,182
用 OpenAI 家的 model 做 personal agent 是灾难,完全是一个正向例子,为什么可以这么难用。
才一天我的 grok bot 用量就去掉了 50% … @bot 管管?
116
Leechael retweeted
老黄太夸张了... 成功是必然的啊
217
584
85
7,447
1,594,889
才一天我的 grok bot 用量就去掉了 50% … @bot 管管?
1
1
307