I don't want to curse it, but @1Password has been working on macOS Safari almost flawlessly for the past few weeks.
First time since I can remember since they rolled out v7 a few years ago.
First time since I can remember since they rolled out v7 a few years ago.
2
0
8
1,270
Probably more capable than a $300 Apple TV
OmarchyTV is officially live on GitHub! 🚀🖥️
Huge thank you to @dhh and @kdaigle for helping get my GitHub account back online so quickly.
26 MIT themes, AI TUI, MCP, Android TV, webOS & PC plugin:
github.com/piermark/omarc…
Computers and TVs should be fun and look cool.
0
0
3
380
This dude is assuming SpaceX is building cell towers and running cables to them.
Not hard to imagine a future where every Tesla has a built-in Starlink that becomes a cell repeater in dense urban areas.
Not hard to imagine a future where every Tesla has a built-in Starlink that becomes a cell repeater in dense urban areas.
Verizon's CEO said today that SpaceX will need at least 4-6 years and $300B-$500B to fully build out its @Starlink Mobile U.S. carrier network:
"Their service just can't compete with a terrestrial network. In suburban and urban areas, where 98% of our revenues are, we're 1,000x more efficient than they are. We know exactly what they're going to do. We know who they're talking to on towers. There's no magic wand. There's no secret sauce. There's no shortcut.
They're going to look at 65,000–80,000 macro sites. They're going to need backhaul, RAN, and a tremendous amount of spectrum. It's going to take a minimum of four to six years to fully build that out. It's going to cost hundreds and hundreds of billions of dollars, I assume somewhere between $300 billion and $500 billion.
Then they need to build retail, customer service, back office systems, et cetera. All of that gets them basically the same network and same capabilities and same cost structure as what we have today. Then sometime over the next four to six years, they have the possibility of becoming the sixth, not the fourth, the sixth competitor in the market.
You can be sure over these next three to five years or six years, we are not going to be standing still. Four to five years from now, we will be two to three generations better than where we are today. We will have high-speed broadband gig-plus coverage across the country with our millimeter wave. We are ahead of most people and already experimenting with what 6G applications will look like."
(via Verizon's Q3 earnings call earlier this morning)
0
0
4
408
My main driver would be an iPad Pro with a Moonlander keyboard if Omarchy ever gets that far.
A single command to install @omarchy on your iPad
Coming soon
Video is sped up, total install took 3.8 minutes
@OmarchyMac @OmarchyUpdates @dhh @OmarchyLinux @tcballard
0
0
3
443
Could somebody in academia explain why mathematicians are so pissed about AI? I’ve heard it described as an “existential threat”!
I’d be stoked if I suddenly had a fleet of computers doing all the grunt work for proofs. I’d start dreaming up even crazier ideas to explore.
I’d be stoked if I suddenly had a fleet of computers doing all the grunt work for proofs. I’d start dreaming up even crazier ideas to explore.
Announcing three major scientific discoveries, one each in mathematics (harmonic analysis), computer science (complexity theory), and physics (quantum field theory).
AI starting to help us improve our understanding of the universe! openai.com/index/building…
1
0
2
537
Has anybody hooked Claude or Codex up to a Remarkable tablet yet?
Seems like it could be a great device for building software.
Seems like it could be a great device for building software.
i started having my agents print off technical (nasa like) review sheets for when they have stuff ready for me
i also got some newsprint and it feels so authentic and good to use
3
0
0
256
I should try hooking up OpenAI's models to my telescope since their model names fit the theme.
GPT-6.1 Terra continues to advance the cost-intelligence frontier across our model families.
It’s a significant step up over GPT‑5.6 Terra, with 50% lower standard API prices.
In ChatGPT Work and Codex, your usage allowance goes further with GPT‑6.1 Terra than with GPT‑5.6 with GPT‑6.1 Sol or GPT‑6 Astra.
For in-depth research or complex coding, choose GPT-6.1 Sol or GPT-6 Astra.
0
0
1
248
Playing with a new hybrid app framework called HyperKit that's like Turbo Native on steroids. It would make @htmx_org blush.
Still quite a bit of work to do, but its surprisingly responsive on desktop & mobile, to the point where you won't really know if it's native or not.
Still quite a bit of work to do, but its surprisingly responsive on desktop & mobile, to the point where you won't really know if it's native or not.
How do we feel about a GBrain macOS app?
🤔
2
1
8
783
@htmx_org ton of prior art I considered.
Turbo Native is obviously an inspiration for a lot of this, but I never liked its navigation model for apps because apps don't work that way.
This is Elixir, so I looked at LiveView Native and didn't go that route. I wanted something that was tied into the LiveView abstraction, and I think I've figured that out.
Ultimately I'm going to continue to FAFO with this for a while until I land on something decent and then open-source Hyperkit.
Turbo Native is obviously an inspiration for a lot of this, but I never liked its navigation model for apps because apps don't work that way.
This is Elixir, so I looked at LiveView Native and didn't go that route. I wanted something that was tied into the LiveView abstraction, and I think I've figured that out.
Ultimately I'm going to continue to FAFO with this for a while until I land on something decent and then open-source Hyperkit.
0
0
2
136
It's not Electron either. The macOS app you see depicted above weighs in at a whopping 1.5Mb because it's a SwiftUI app that uses Webkit's APIs to render web services on UI surfaces that can swipe around, pop-over other surfaces, etc.
0
0
1
65
I have @terminalwire broken out amongst many repos and can confirm multi repos are very easy with agents and work well.
i think i kept seeing people say "monorepos are good for agents"
but we just switched to multi repos. i have a hard time caring about the benefits of monorepos anymore
0
0
2
615
FAFO is the way.
the best part of “fuck around and find out” was the dopamine of finding out what you were gonna find out
but then agents made the fucking around part so much faster and cheaper, that i find now that i am finding A LOT of things out
but because of this new abundance of finding things out, i eventually found that the finding out part was not as exciting anymore
so i started upping the ante and had the agents REALLY fuck around so i could find some quite spectacular things out
0
0
1
371
Hosted GBrain now starts at $49/mo! This is a nice unlock for solo founders or people who regularly use multiple AIs and want to keep them in sync.
I use Claude Code to build stuff and ChatGPT for everything else, so its nice having them synced with the same memory & tools.
I use Claude Code to build stuff and ChatGPT for everything else, so its nice having them synced with the same memory & tools.
Your agents shouldn't each start from zero
We built a personal plan of GBrain for founders. Claude, Codex and Capy can now share one memory of who you know and how you execute
gbrain.io/personal?v=2
0
1
3
518
Life is more complicated than "Personal" and "Work", which is why we spent extra time on account switching in @gbrainio.
I use it to run my personal life, @polleverywhere, SaaS, & GBrain.
@garrytan uses it to run the many facets of his life & business.
gbrain.io/notes/switchin…
I use it to run my personal life, @polleverywhere, SaaS, & GBrain.
@garrytan uses it to run the many facets of his life & business.
gbrain.io/notes/switchin…
0
4
10
5,247
What happened to porting everything into Rust?
Has everything been ported and we don’t talk about it anymore?
Has everything been ported and we don’t talk about it anymore?
0
0
3
309
Brad Gessler retweeted
We're here to make AI work better together whether its sharing memory, skills, or tools across OpenAI, Claude, GrokBot, or any other AI.
We have non-technical teams using us because half prefer OpenAI & the other Claude. We connect them so they can choose the best tool.
We have non-technical teams using us because half prefer OpenAI & the other Claude. We connect them so they can choose the best tool.
i run 5 claude code chats in parallel on one product. The problem is, they kept stepping on each other which resulted in duplicate work and decisions made in one chat that the others never heard about
so I made one chat the engineering manager. It keeps a single shared board sks every chat "what did I tell you that isn't on the board?", and messages each chat only what changes for it.
its first sweep found ~20 decisions that had never left the chat they were made in.
i highly recommend this for anyone else running multiple parallel agents
14
1
23
970
Kinda nice seeing how all of my AI agents are using my apps with gbrain.io/tools.
Here I can see Stripe is being called by some internal revenue analysis agents.
Here I can see Stripe is being called by some internal revenue analysis agents.
2
1
6
444