Founder & CEO | Quincy Labs | AGI Sickle Cell Warrior | RCS 🩸 🧬Engineer, BlockHaven — Building The Health Intelligence Network™ https://teapawt.org/t.co/FRx1NrRKmd
NYC🗽
Joined April 2021
- Tweets9.8K
- Following3.3K
- Followers316
- Likes51.1K
Pinned Tweet
Anthropic just put Claude in Slack as a "team member" — channel-scoped identity, memory, tools, async task delegation, spend limits, action logs, and optional ambient behavior that follows quiet threads and surfaces relevant context.
I shipped the local version of this the day before.
That's the whole point of the piece: ambient agents are moving from weird personal setup → enterprise product category. Same architecture, different trust boundary.
An ambient agent isn't a chatbot with Slack access. It's a persistent, context-bearing operator embedded in the room's workflow:
• room awareness
• mention escalation
• source-checking before it speaks
• memory/instructions as the control plane
• restraint by default
Their lane: hosted enterprise SaaS with admin controls.
My lane: local/private personal runtime, tools living closer to the machine.
Hosted enterprise agent vs local/private personal agent is going to be one of the defining splits.
@bcherny @_catwu @trq212
New post 👇
🤖 Made with AI
Henry Ogedegbe Jr. retweeted
This is HUGE for using Claude to organize your real life.
Duet can now work across your @claudeai Projects
Old way: projects -> multiple threads, but you had to switch between projects
New way: Duet -> multiple projects -> multiple threads, so you can work across anything from one interface
long live the mega-thread meta!
Henry Ogedegbe Jr. retweeted
Introducing Rex Claude
A Claude Code skill that lets Claude control Rex terminal panes and tabs
After spending quite some time experimenting with Rex, I built this skill to let Claude open new panes, launch independent Claude Code sessions, and coordinate work between them
Sessions can exchange instructions, monitor progress, and detect when another session finishes or needs attention
All orchestrated directly from Claude Code
Installation:
npx claude-code-templates@latest --skill productivity/rex-claude
aitmpl.com/component/skill/p…
Henry Ogedegbe Jr. retweeted
The more I use Rex by @superlogical... the more I like it!
This weekend I’m going all in. I want to explore everything Rex has to offer, especially how to get the most out of it when working with Claude Code
A complete deep dive article is coming soon, with my setup, workflows, and everything I learn along the way
Really happy with this terminal so far!
Henry Ogedegbe Jr. retweeted
we will need to rebuild and rewrite much of software to adapt to a new, faster pace.
code used to arrive one drop at a time. soon, if not already, code will be written as if it were a continuous stream, like a violent river twisting and turning as it pleases.
this is not a new thing: big tech cos have had to deal with this with the enormous scale of their engineering teams. but now ai has brought an incredibly elastic and capable workforce wielded by every engineer. this is your problem now, and the only way to adapt is to evolve your systems so agents - even and especially the ones with little context about the right way of doing things - can thrive. make the easy thing the right thing.
your codebase is becoming organic architecture. agent contributions grow around the constraints and guardrails you’ve designed. good software engineering matters even more now! and no, the continuous stream of code is not something you have to watch helplessly. be more ambitious and design systems, frameworks, and languages to control the chaos.
the time for mourning coding is long over
Henry Ogedegbe Jr. retweeted
Already testing Rex by Superlogical, and I have one word so far... beautiful 🤩
I've been using Ghostty for a while, and switching to Rex feels surprisingly natural
The left sidebar with all my sessions, the split panes, the clean UI, and how smooth everything runs, I'm loving it so far
Next up: setting up Tailscale so I can access my sessions directly from my phone.
A full hands-on tutorial is coming soon!
Henry Ogedegbe Jr. retweeted
Close, but wrong direction. Let’s build a new modern window server starting from terminal primitives so we can eventually build better GUIs. As a hint, the Rex server has zero knowledge about terminals :) they’re just an app.
Henry Ogedegbe Jr. retweeted
有人发现了一种非常离谱的 JavaScript 混淆技术：通过在代码里塞入大量生物武器、毒药和致死剂量相关的函数名，让 AI 因为安全限制而拒绝分析代码。
安全研究员 veritas 在分析浏览器指纹脚本时，发现一段来自 ServicePipe 相关域名的 JavaScript，里面充斥着极其诡异的函数名：
computeRicinLethalDosageForWaterSupply
calculateDeadlyLethalSuicideAspirinDosage
光看名字，仿佛在研究生化武器。但实际上，这段代码只是在收集浏览器指纹，包括 User-Agent、GPU、Canvas 等信息。
研究员怀疑，这些名字是开发者故意设置的陷阱，专门用来阻止 AI 辅助逆向工程。
于是他做了个实验：
• Astra：拒绝分析
• Astra + Daybreak Blue：仍然拒绝
• GLM-5.3：成功分析
这就有意思了。
传统代码混淆是通过复杂控制流、加密字符串、无意义变量名，让人类和工具难以理解代码。
而这种新思路，直接瞄准了大模型的安全机制。
代码本身可能完全无害，但只要在函数名里塞进足够多的危险词汇，部分 AI 就可能主动放弃分析。
更讽刺的是，模型越严格遵守某些安全规则，面对这种混淆时反而可能越容易受到干扰。
当然，目前还没有证据证明开发者一定是故意这样设计，也不能说明这种方法对所有模型都有效。
但它揭示了一个值得关注的趋势：随着越来越多的逆向工程依赖 AI，未来的代码混淆技术可能不再只针对编译器、反编译器和人类研究员，还会专门针对大模型的安全判断机制。
以前是让代码难以理解，现在甚至可以尝试让 AI 不敢理解。
Henry Ogedegbe Jr. retweeted
If you have an Apple developer account or an app in the App Store, read this now and share it.
Apple rejects your app. The notice is vague, so you fix what you reasonably think is wrong and resubmit.
Apple approves it.
Months later, with nothing in review, Apple terminates your account under 3.2(f) for “a pattern of manipulative or misleading behavior.” Every app gone. No explanation of what you did.
Your crime? Trusting the approval.
Apple’s own reviewer looked at your fix, with your rejection history in front of them, and said yes. Then Apple turned that yes into evidence against you.
So who’s misleading whom?
I ran App Review for seven years and wrote the guidelines. 3.2(f) used to mean real fraud. Now it’s being used against developers who did exactly what Apple approved.
I’ve made this Substack post free for everyone. Every developer needs to see it before this happens to them.
Share it before someone you know gets that email.
phillipshoemaker.substack.co…
Henry Ogedegbe Jr. retweeted
A quick demo of floating panes in Rex, some of their features, and how I use them in my daily workflow. I think our implementation of floating panes looks great and feels great and I think you'll love it! These are also all scriptable and API driven, too, of course!
Henry Ogedegbe Jr. retweeted
good things we got in 28 days
• default context window up from 272k to 500k, no long context surcharge for subs
• prompts are cached for 12 hours
• subagents use cache when they are forked off
• 6.1 sol ultrafast in $500 plan
• inference optimizations, 50% faster sol and astra
• 6.1 terra released
• free auto review
Day 26/ You can now easily switch between multiple accounts on mobile, and coming soon to desktop too. Next two days will be resets… banked… do with this what you may 👀.
help.openai.com/en/articles/…
Henry Ogedegbe Jr. retweeted
Excited to announce that Apple has taken on maintainership of the Swift MCP SDK. I’m grateful for Apple’s engagement with the MCP community.
github.com/modelcontextproto…
Henry Ogedegbe Jr. retweeted
"It was such a brutal time getting this company going..."
@AnjneyMidha tells the story of how 21 Investors Said No to Anthropic
Some didn't even know what GPT-3 was…
Henry Ogedegbe Jr. retweeted
There is an absolutely WILD story in this @GergelyOrosz podcast episode
1. An unnamed CTO of a cash-flow-negative company was debating doing layoffs. AI
2. He says "I don't want to hurt morale like that, I won't do it"
3. A few months later, he says to @GergelyOrosz that he's cash flow positive. WTF. How?
4. The company had been licensing a component from a licensing company that was critical for their business.
5. One day, a dev thinks "what if we got an agent to build our own?"
6. The agent does so well that they produce a BETTER, FASTER version of the component they were licensing.
7. They debate open-sourcing it, and they ask the licensing company about it
8. The licensing company panics, and says "we will pay you NOT to open-source this"
9. They also say "we'll also pay you extra so we can re-license it"
10. So a big outlay became a recurring windfall, thanks to the ingenuity of a dev asking the right question.
Individual contributors have never been more powerful. Think bigger.
youtu.be/mQu0zN4IvSI?si=P_v9…
Henry Ogedegbe Jr. retweeted
experimenting with a lil personal project: an AI-native macOS dock with custom modes (writing, building, etc.) to help me stay focused
my agent is able to customize mode behavior and add new modes, it uses jev to classify my activity + notifications in real time & act on them
Henry Ogedegbe Jr. retweeted
Ghostty 1.4 is now out! Full Kitty graphics with animation (the first terminal besides Kitty to do it), scrollback compression for much lower memory usage, macOS 27 support, a new OpenGL renderer on Linux, ghostty +ssh, big performance gains, and hundreds more changes.
The highlights:
- Scrollback compression: scrollback compresses ~90+% on average, meaning your terminals use that much less live memory
- Huge memory savings across the board: no single large thing, just lots of good improvements lowers memory usage everywhere, netting anywhere from 50 to 90% less memory usage depending on workload
- Kitty graphics is now 100% complete, including animation and relative placements, after a full conformance pass against the spec and Kitty itself
- The Kitty clipboard protocol, with an image preview when a program asks to read your clipboard
- Split drag and drop on Linux, including between windows
- ghostty +ssh installs terminfo on remote hosts automatically, so things just work over SSH
- Lots of terminal emulation accuracy fixes
This release is 7 months of work from 172 contributors over 2,889 commits. It also fixes 10 security advisories, so please update.
Full release notes: ghostty.org/docs/install/rel…
