Загрузка видео...

Не удалось загрузить видео

Возникла проблема при загрузке этого видео. Это может быть связано с временными проблемами сети или видео может быть недоступно.

На главную

Friday sideproject - wrapped OpenAI Operator into a native MacOS app So far I have - 1 Operator window instead of 100 tabs - Native notifications! - Menu bar with unread status - Raycast extension Launching agents from Raycast feel like magic 🪄

Alex Volkov

41,058 subscribers

28,219 просмотров • 1 год назад •via X (Twitter)

Образование Наука и технологии Юмор

Anya Rossi• Live Now

Private livecam show

Комментарии: 11

Фото профиля Dominick Romano

Dominick Romano1 год назад

@OpenAI @raycastapp Ok, so if you don't put your passwords in the app or chat window, does it still work with your accounts??

Фото профиля AI路子野

AI路子野1 год назад

@OpenAI @raycastapp What’s this screen recording app

Фото профиля Philipp Tsipman

Philipp Tsipman1 год назад

Now you just need a computer use agent to drive all the browser use agents :-)

Фото профиля CodeRabbit

CodeRabbit1 год назад

AI-first pull request reviewer with context-aware feedback, line-by-line code suggestions, and real-time chat.

Фото профиля Harshal

Harshal1 год назад

@OpenAI @raycastapp Magician!

Фото профиля Pierre Vannier

Pierre Vannier1 год назад

@OpenAI @raycastapp So cool Alex !!

Фото профиля daniel wilson

daniel wilson1 год назад

@OpenAI @raycastapp Have you successfully gotten operator to pip install on a web IDE?

Фото профиля Alex Volkov (Thursd/AI)

Alex Volkov (Thursd/AI)1 год назад

@OpenAI @raycastapp Don't see the point operator coding , it only sees pixels Maybe if it talks to cursor 🤔

Фото профиля Peter Welinder

Peter Welinder1 год назад

@OpenAI @raycastapp Wow! Neat idea and implementation.

Фото профиля Alex Volkov (Thursd/AI)

Alex Volkov (Thursd/AI)1 год назад

@OpenAI @raycastapp Thanks Peter! I got tired of clicking the browser notification and have it open a new tab tbh Until you guys ship a desktop app, I'll be launching Agents with @raycastapp

Фото профиля Bee 🐝

Bee 🐝1 год назад

@OpenAI @raycastapp Fire

Похожие видео

Nice feature coming to Ghostty on macOS: keep window on top! Can be toggled via both the native menu bar, command palette, or bound to a key. This is a common macOS app feature (e.g. provided by Notes, Calculate, etc.). Feels right. 🥰 (For Linux/GTK users: this should be done at your WM/DE level instead of Ghostty which is more idiomatic. There doesn't seem to be a Wayland protocol for this and I didn't dare even look at the X11 atom nightmare fuel.)

Nice feature coming to Ghostty on macOS: keep window on top! Can be toggled via both the native menu bar, command palette, or bound to a key. This is a common macOS app feature (e.g. provided by Notes, Calculate, etc.). Feels right. 🥰 (For Linux/GTK users: this should be done at your WM/DE level instead of Ghostty which is more idiomatic. There doesn't seem to be a Wayland protocol for this and I didn't dare even look at the X11 atom nightmare fuel.)

Mitchell Hashimoto

47,170 просмотров • 1 год назад

CleanShot X is great. The subscription isn't. So I rebuilt BetterShot from the ground up native Swift, zero web views, zero tauri. BetterShot now runs natively on macOS, powered by Swift 6 + SwiftUI. Here's what you get for free, forever: - Region, fullscreen & window capture - Beautiful backgrounds gradients, solids, macOS wallpapers, custom images - Annotations arrows, shapes, text, blur, spotlight, numbered badges - OCR text extraction + QR/barcode scanning - Color picker - Pin screenshots as floating windows - Self-timer with countdown overlay - Capture history - In-app updates - Lives in your menu bar. No Dock clutter. Local-first. No cloud. No telemetry. No subscription. Open source → Try it →

CleanShot X is great. The subscription isn't. So I rebuilt BetterShot from the ground up native Swift, zero web views, zero tauri. BetterShot now runs natively on macOS, powered by Swift 6 + SwiftUI. Here's what you get for free, forever: - Region, fullscreen & window capture - Beautiful backgrounds gradients, solids, macOS wallpapers, custom images - Annotations arrows, shapes, text, blur, spotlight, numbered badges - OCR text extraction + QR/barcode scanning - Color picker - Pin screenshots as floating windows - Self-timer with countdown overlay - Capture history - In-app updates - Lives in your menu bar. No Dock clutter. Local-first. No cloud. No telemetry. No subscription. Open source → Try it →

Kartik

84,305 просмотров • 1 месяц назад

Zeity for macOS is live 🦉✨ 9am standup - lagos, berlin, são paulo. i'm doing timezone math in my head before i've even opened slack. That's been the last few years of remote work for me, quietly tracking when teammates are awake, asleep, eating lunch, signing off. The Chrome extension i built (Zeity v1) helped, but it was always one tab away from being ignored. So i ported it to the Mac and rewrote the whole thing in Swift. Zeity for Mac lives in your menu bar — your friends' and teammates' local times always one click away. No new tabs, no calendar plugins, no math. What's in it 👇🏽: - Search timezones by city or local place, not just timezone names (Apple's native APIs do the heavy lifting) - Native widgets: Clock, Friends, Timezones - Launch at login, runs quietly, low cpu usage (near 0) - AppleScript support for the automation lovers - One-click in-app updates → Download: → Not on a Mac? Zeity also lives as a Chrome extension, works on any OS → A simple solution I needed, now for everyone.

Zeity for macOS is live 🦉✨ 9am standup - lagos, berlin, são paulo. i'm doing timezone math in my head before i've even opened slack. That's been the last few years of remote work for me, quietly tracking when teammates are awake, asleep, eating lunch, signing off. The Chrome extension i built (Zeity v1) helped, but it was always one tab away from being ignored. So i ported it to the Mac and rewrote the whole thing in Swift. Zeity for Mac lives in your menu bar — your friends' and teammates' local times always one click away. No new tabs, no calendar plugins, no math. What's in it 👇🏽: - Search timezones by city or local place, not just timezone names (Apple's native APIs do the heavy lifting) - Native widgets: Clock, Friends, Timezones - Launch at login, runs quietly, low cpu usage (near 0) - AppleScript support for the automation lovers - One-click in-app updates → Download: → Not on a Mac? Zeity also lives as a Chrome extension, works on any OS → A simple solution I needed, now for everyone.

P!

16,668 просмотров • 2 месяцев назад

This weekend, I explored a mobile game idea with my kids (they suggested a mobile pokemon-like game) so I had them coming up with ideas for the creatures and I try to visualise them with ChatGPT Images 2.0 and vibe coded a small prototype on Cursor to play around with. The art direction of the creatures are in vinyl toy matte style so it has this toy-like aesthetic quality that I quite like! For a mobile app/game, I went with Expo + React Native to create this mobile app so that I have one code-base for both Android and iOS. So far I'm pretty impressed with Expo's live mobile app preview feature! Being able to easily preview the mobile app on my phone in seconds is a big plus.

This weekend, I explored a mobile game idea with my kids (they suggested a mobile pokemon-like game) so I had them coming up with ideas for the creatures and I try to visualise them with ChatGPT Images 2.0 and vibe coded a small prototype on Cursor to play around with. The art direction of the creatures are in vinyl toy matte style so it has this toy-like aesthetic quality that I quite like! For a mobile app/game, I went with Expo + React Native to create this mobile app so that I have one code-base for both Android and iOS. So far I'm pretty impressed with Expo's live mobile app preview feature! Being able to easily preview the mobile app on my phone in seconds is a big plus.

Danny Limanseta

37,093 просмотров • 2 месяцев назад

i don't hate terminals but i hate complexity of tmux/zellij har session management w/ attach/detach rituals + resurrection plugins + naming sessions 🤢 it's a part-time job just to not lose your layout / tabs. burned 40-50 hours trying every multi-agent manager out there, including stuff from my YC-backed friends are actively shipping. forked even some of them but nothing fully clicked to my workflow. turns out all i wanted was already sitting inside one terminal window. vs tmux/zellij: - mouse first, click anything (right click too) - zero shortcuts to memorize (native shortcuts) - custom keybinds if you want them (fully configurable) - rename tabs + spaces inline (⌘+L / ⌘ + K / ⌘ + 1..9) - single window = a lot less RAM / CPU usage - stability and rendering are world-class - ⌘+Q anytime. state saved. re-run it later (even on ssh) and everything's exactly where you left it. no plugins, no two step shortcuts, just works out of box (i've shared my keyboard bindings if you wanna combine with ghostty) then i wired it into ghostty with a custom installer. cmd+t, cmd+n, chrome-style tab cycling and number-jumping, all native. drop-in cmux replacement. finally feels like macos to me. video below. my ⌘-based shortcut installer in reply ☠️

i don't hate terminals but i hate complexity of tmux/zellij har session management w/ attach/detach rituals + resurrection plugins + naming sessions 🤢 it's a part-time job just to not lose your layout / tabs. burned 40-50 hours trying every multi-agent manager out there, including stuff from my YC-backed friends are actively shipping. forked even some of them but nothing fully clicked to my workflow. turns out all i wanted was already sitting inside one terminal window. vs tmux/zellij: - mouse first, click anything (right click too) - zero shortcuts to memorize (native shortcuts) - custom keybinds if you want them (fully configurable) - rename tabs + spaces inline (⌘+L / ⌘ + K / ⌘ + 1..9) - single window = a lot less RAM / CPU usage - stability and rendering are world-class - ⌘+Q anytime. state saved. re-run it later (even on ssh) and everything's exactly where you left it. no plugins, no two step shortcuts, just works out of box (i've shared my keyboard bindings if you wanna combine with ghostty) then i wired it into ghostty with a custom installer. cmd+t, cmd+n, chrome-style tab cycling and number-jumping, all native. drop-in cmux replacement. finally feels like macos to me. video below. my ⌘-based shortcut installer in reply ☠️

Yigit Konur

49,775 просмотров • 2 месяцев назад

🚨 This is a $3,000-$5,000 service hiding in plain sight 🚨 Most local businesses still don’t have a mobile app because they assume it costs $50K+ and takes months to build. The play: < Find businesses with solid websites but no app: restaurants, gyms, salons, clinics, etc. < Use this tool to turn their existing website into a native mobile app < Customize the design, add push notifications, booking, payments, or loyalty features < Charge $3,000-$5,000 for the build + $200/month to maintain it < Deliver it in days instead of months To them it's black magic. To you it's just copy/pasting a URL. 10 clients = $2,000 MRR before even counting the setup fees. Let that sink in...

🚨 This is a $3,000-$5,000 service hiding in plain sight 🚨 Most local businesses still don’t have a mobile app because they assume it costs $50K+ and takes months to build. The play: < Find businesses with solid websites but no app: restaurants, gyms, salons, clinics, etc. < Use this tool to turn their existing website into a native mobile app < Customize the design, add push notifications, booking, payments, or loyalty features < Charge $3,000-$5,000 for the build + $200/month to maintain it < Deliver it in days instead of months To them it's black magic. To you it's just copy/pasting a URL. 10 clients = $2,000 MRR before even counting the setup fees. Let that sink in...

Shipper

11,095 просмотров • 2 месяцев назад

There's probably $100+ billion up for grabs for people who build startup for AI agents Over the next 10 years you're going to have a market of billions of customers (agents) with millions of wallets that want to use your services. TLDR; The internet was built for people: 1. Search google 2. Read landing page 3. Book demo 4. Talk to sales 5. Buy Agents don’t do that. Agents will: 1. Ask which product to use 2. Read your docs/pricing/security pages 3. Compare you to competitors 4. Check if you have an MCP/API/tool layer 5. Buy or recommend you without ever “visiting” your site like a person Everyone is going to have personal agents and business agents. This feels inevitable at this point. OpenClaw, Hermes, Claude Code, Codex, Google Spark. The tools are here. Which means there will be more agents on the internet than humans. So, where's the opportunity?? Go look at every SaaS tool you use. Notion. Slack. Jira. Google Analytics. Now ask: what is the version of this built purely for agents? Agent-native payments. Agent-native communication. Agent-native memory. Every category gets rebuilt. I clearly break down this shift and explain you everything on today's ep of The Startup Ideas Podcast (SIP) 🧃. Over the next 10 years you're going to have a market of billions of customers (agents) with millions of wallets that want to use your services. The founders who build for them now are going to look like the people who built websites in 1995. Might feel janky at the moment, but also obvious in hindsight. This is the next shift. Link over here: Watch

There's probably $100+ billion up for grabs for people who build startup for AI agents Over the next 10 years you're going to have a market of billions of customers (agents) with millions of wallets that want to use your services. TLDR; The internet was built for people: 1. Search google 2. Read landing page 3. Book demo 4. Talk to sales 5. Buy Agents don’t do that. Agents will: 1. Ask which product to use 2. Read your docs/pricing/security pages 3. Compare you to competitors 4. Check if you have an MCP/API/tool layer 5. Buy or recommend you without ever “visiting” your site like a person Everyone is going to have personal agents and business agents. This feels inevitable at this point. OpenClaw, Hermes, Claude Code, Codex, Google Spark. The tools are here. Which means there will be more agents on the internet than humans. So, where's the opportunity?? Go look at every SaaS tool you use. Notion. Slack. Jira. Google Analytics. Now ask: what is the version of this built purely for agents? Agent-native payments. Agent-native communication. Agent-native memory. Every category gets rebuilt. I clearly break down this shift and explain you everything on today's ep of The Startup Ideas Podcast (SIP) 🧃. Over the next 10 years you're going to have a market of billions of customers (agents) with millions of wallets that want to use your services. The founders who build for them now are going to look like the people who built websites in 1995. Might feel janky at the moment, but also obvious in hindsight. This is the next shift. Link over here: Watch

GREG ISENBERG

55,398 просмотров • 1 месяц назад

Most PMs still think in tasks. Write a PRD. Update JIRA. Review designs. AI native PMs think differently. They think in prompts. .Mike Bal calls it "thinking in prompts" and admits it sounded silly at first. But once you integrate AI into daily work, it becomes natural. Instead of "I need to write a PRD," they think: "What do I need to get done? What are the steps? What are the best tools?" They treat AI as an extension of themselves. Breaking down tasks into instructions and steps. "If you're thinking about AI as like an extension of yourself, you're thinking like, what are the instructions? What are the steps? And if you're reflective, like you probably do that to yourself at some level anyway, you have your inner dialogue, right?" The shift is from task-oriented to process-oriented thinking. It's how you already think internally. AI native PMs just make that process explicit. Lesson: AI native PMs don't just use AI tools. They fundamentally restructure how they think about work, breaking every task into steps and instructions that AI can execute.

Most PMs still think in tasks. Write a PRD. Update JIRA. Review designs. AI native PMs think differently. They think in prompts. .Mike Bal calls it "thinking in prompts" and admits it sounded silly at first. But once you integrate AI into daily work, it becomes natural. Instead of "I need to write a PRD," they think: "What do I need to get done? What are the steps? What are the best tools?" They treat AI as an extension of themselves. Breaking down tasks into instructions and steps. "If you're thinking about AI as like an extension of yourself, you're thinking like, what are the instructions? What are the steps? And if you're reflective, like you probably do that to yourself at some level anyway, you have your inner dialogue, right?" The shift is from task-oriented to process-oriented thinking. It's how you already think internally. AI native PMs just make that process explicit. Lesson: AI native PMs don't just use AI tools. They fundamentally restructure how they think about work, breaking every task into steps and instructions that AI can execute.

Aakash Gupta

16,788 просмотров • 5 месяцев назад

Did Rory McIlroy have a number in mind going into Saturday, and does he think he has a chance come Sunday? "If I had to play the last three holes at 1-under instead of 1-over, I would have got to 5. And I sort of thought if I could go out today and get to that, it would make the leaders shoot under par to either be with me or ahead of me. So I didn't get there. I made, I guess, a couple of mistakes the last three holes. "I feel like I still did enough to think I have a chance going into tomorrow."

Did Rory McIlroy have a number in mind going into Saturday, and does he think he has a chance come Sunday? "If I had to play the last three holes at 1-under instead of 1-over, I would have got to 5. And I sort of thought if I could go out today and get to that, it would make the leaders shoot under par to either be with me or ahead of me. So I didn't get there. I made, I guess, a couple of mistakes the last three holes. "I feel like I still did enough to think I have a chance going into tomorrow."

Cameron Jourdan

137,253 просмотров • 2 месяцев назад

Los Angeles Pacific Palisades fire donations have been laundered to NGOs Money raised for fire victims was sent to NGOs and is being used to promote black equality, efforts focused on getting Native Americans elected into positions of political power and more “Out of $100 million raised for the fire victims of the LA fires, none of that went to any of them. I just find that so strange. Instead they went to a bunch of non government organizations that literally, quite literally have nothing to do with it. California Native Vote Project received $250,000. This organization is to promote political power among the Native American communities across California. What the f*ck does that have to do with the fires that happened in Los Angeles? Pasadena NAACP also received $250,000. Oh, guess what they do a civil rights organization to promote black equality. What the f*ck does that have to do with fire?” “They would so rather help illegal aliens and give them a card of cash than give it to people who lost everything in fires. Sorry, I can't. I f*cking can't.“

Los Angeles Pacific Palisades fire donations have been laundered to NGOs Money raised for fire victims was sent to NGOs and is being used to promote black equality, efforts focused on getting Native Americans elected into positions of political power and more “Out of $100 million raised for the fire victims of the LA fires, none of that went to any of them. I just find that so strange. Instead they went to a bunch of non government organizations that literally, quite literally have nothing to do with it. California Native Vote Project received $250,000. This organization is to promote political power among the Native American communities across California. What the fck does that have to do with the fires that happened in Los Angeles? Pasadena NAACP also received $250,000. Oh, guess what they do a civil rights organization to promote black equality. What the fck does that have to do with fire?” “They would so rather help illegal aliens and give them a card of cash than give it to people who lost everything in fires. Sorry, I can't. I f*cking can't.“

Wall Street Apes

71,605 просмотров • 1 год назад

haha, i used OpenAI operator build, deploy, and open source a tool on github using Replit ⠕ agent. took about 30 min, here's an ~8 min supercut video thoughts: - while working with replit agent, it actually deployed the app, tested it, and described the error back to replit agent for me - operator asked me a few more Qs than i wanted, but it was mostly for safety (eg filling forms) so i guess okay with it - it had trouble with a few things around UI like knowing it needs to scroll a page to see the rest of it, and it needed pointers to find the git feature in replit - once it found the git feature it didn't need my assistance to create a repo and open source after having the agent write a readme while a bit slower, this was even more automated than replit agent (especially testing features and working through errors) - which is impressive would be nice to have: push notifications for when it needs my attention, and voice mode capabilities

haha, i used OpenAI operator build, deploy, and open source a tool on github using Replit ⠕ agent. took about 30 min, here's an ~8 min supercut video thoughts: - while working with replit agent, it actually deployed the app, tested it, and described the error back to replit agent for me - operator asked me a few more Qs than i wanted, but it was mostly for safety (eg filling forms) so i guess okay with it - it had trouble with a few things around UI like knowing it needs to scroll a page to see the rest of it, and it needed pointers to find the git feature in replit - once it found the git feature it didn't need my assistance to create a repo and open source after having the agent write a readme while a bit slower, this was even more automated than replit agent (especially testing features and working through errors) - which is impressive would be nice to have: push notifications for when it needs my attention, and voice mode capabilities

Yohei

211,889 просмотров • 1 год назад

BREAKING 🚨 Anthropic just unveiled "Cowork," a major feature that turns Claude into a fully autonomous virtual assistant for everyone. It brings the deep agentic capabilities previously reserved for coders to general users, allowing Claude to perform complex tasks directly on your computer. The tool was built after Anthropic noticed developers using "Claude Code" for everyday admin tasks. Cowork now lets anyone grant Claude access to folders to manage files, research, and complete multi-step workflows independently acting as a digital employee that "does" instead of just chats. Cowork is available today as a research preview for Claude Max subscribers on the macOS app 😡. Claude is releasing new coding/desktop agents much faster than all of there competitors. This launch exposes a massive gap in the current AI landscape: in 2026, Google still explicitly lacks a consumer browser agent, and xAI has yet to release a native CLI or agentic interface. While OpenAI has "Operator" and Google has the developer-focused "Antigravity," Anthropic is now the only other major lab providing a true "do-it-for-me" experience for general users.

BREAKING 🚨 Anthropic just unveiled "Cowork," a major feature that turns Claude into a fully autonomous virtual assistant for everyone. It brings the deep agentic capabilities previously reserved for coders to general users, allowing Claude to perform complex tasks directly on your computer. The tool was built after Anthropic noticed developers using "Claude Code" for everyday admin tasks. Cowork now lets anyone grant Claude access to folders to manage files, research, and complete multi-step workflows independently acting as a digital employee that "does" instead of just chats. Cowork is available today as a research preview for Claude Max subscribers on the macOS app 😡. Claude is releasing new coding/desktop agents much faster than all of there competitors. This launch exposes a massive gap in the current AI landscape: in 2026, Google still explicitly lacks a consumer browser agent, and xAI has yet to release a native CLI or agentic interface. While OpenAI has "Operator" and Google has the developer-focused "Antigravity," Anthropic is now the only other major lab providing a true "do-it-for-me" experience for general users.

Chris

501,963 просмотров • 6 месяцев назад

Tune into EP 1 of cozy lofi design corners 🌱: I interview zade ⠕ who built and launched an incredible mobile app into the App Store, all through Replit. ~~~~~ Today Replit ⠕, we’re introducing the easiest way to vibe code mobile apps and publish them to the App Store. I remember back when I built my first mobile app, I sat beside engineers for hours trying to make the native experiences feel just right. The haptics, the bottom sheet transitions, and more. Mobile App development has always been such a headache. Now, with Replit Agent, it’s truly just a prompt away. This is by far one of my most favorite projects I’ve worked, alongside the power team (ink, armaan, jordwalke, Laima, Milos, and more). Try it now, and send feedback my way! This is just the beginning.

Tune into EP 1 of cozy lofi design corners 🌱: I interview zade ⠕ who built and launched an incredible mobile app into the App Store, all through Replit. ~~~~~ Today Replit ⠕, we’re introducing the easiest way to vibe code mobile apps and publish them to the App Store. I remember back when I built my first mobile app, I sat beside engineers for hours trying to make the native experiences feel just right. The haptics, the bottom sheet transitions, and more. Mobile App development has always been such a headache. Now, with Replit Agent, it’s truly just a prompt away. This is by far one of my most favorite projects I’ve worked, alongside the power team (ink, armaan, jordwalke, Laima, Milos, and more). Try it now, and send feedback my way! This is just the beginning.

vic

12,994 просмотров • 6 месяцев назад

Woo hoo! OpenAI highlights HubSpot partnership on main stage at #DevDay. Today was a special day for me. Was so cool to see Sam Altman from OpenAI feature HubSpot from the main keynote stage at their Dev Day event. HubSpot and OpenAI are the two most impactful companies in my life. HubSpot, for obvious reasons and OpenAI for less obvious ones. My relationship with Sam and OpenAI goes back a bit: 1) Got access to the GPT-2 API so had my "moment of magic" well before ChatGPT launched. 2) Have been using OpenAI's APIs and platform to build apps and agents for years. They *really* understand developers and have an amazing dev experience. 3) Sold the chat .com domain name to them and as a result was able to become an investor in the company. 4) They're the primary AI platform that HubSpot partners with and builds with -- as highlighted today. My congrats to the entire OpenAI team for today's event. I know how much work goes into putting together an event like this. And it was clear from the vibes how much you folks *care*. Cheers.

Woo hoo! OpenAI highlights HubSpot partnership on main stage at #DevDay. Today was a special day for me. Was so cool to see Sam Altman from OpenAI feature HubSpot from the main keynote stage at their Dev Day event. HubSpot and OpenAI are the two most impactful companies in my life. HubSpot, for obvious reasons and OpenAI for less obvious ones. My relationship with Sam and OpenAI goes back a bit: 1) Got access to the GPT-2 API so had my "moment of magic" well before ChatGPT launched. 2) Have been using OpenAI's APIs and platform to build apps and agents for years. They really understand developers and have an amazing dev experience. 3) Sold the chat .com domain name to them and as a result was able to become an investor in the company. 4) They're the primary AI platform that HubSpot partners with and builds with -- as highlighted today. My congrats to the entire OpenAI team for today's event. I know how much work goes into putting together an event like this. And it was clear from the vibes how much you folks care. Cheers.

dharmesh

57,875 просмотров • 9 месяцев назад

Ghostty 1.3 is going to have a preview of AppleScript support. All windows, tabs, splits, terminals are exposed via AppleScript. For macOS users, this satisfies some of the most common requests: broadcast commands, automatic layouts, jump to working directory, etc. PR here: I also think this is an incredibly important feature to ship early/now so agentic tools like Claude and Codex can take advantage of a scriptable Ghostty on macOS. I still plan on a generic cross-platform scripting/plugin API (two separate things), but integrating with native features like AppleScript is entirely in scope of the Ghostty mission and like our Shortcuts integration it importantly lets you connect multiple sources since AppleScript can control multiple applications from one script. Note I normally don't ship features so down to the wire with a release, but this one is very isolated in its impact and I'm going to explicit document it in the release notes and website as a preview since I fully expect we're going to iterate a lot on the objects and commands exposed. From a security perspective, Apple already prompts for permission to control different applications so we're covered, but there is a master kill switch you can put in the config, too.

Ghostty 1.3 is going to have a preview of AppleScript support. All windows, tabs, splits, terminals are exposed via AppleScript. For macOS users, this satisfies some of the most common requests: broadcast commands, automatic layouts, jump to working directory, etc. PR here: I also think this is an incredibly important feature to ship early/now so agentic tools like Claude and Codex can take advantage of a scriptable Ghostty on macOS. I still plan on a generic cross-platform scripting/plugin API (two separate things), but integrating with native features like AppleScript is entirely in scope of the Ghostty mission and like our Shortcuts integration it importantly lets you connect multiple sources since AppleScript can control multiple applications from one script. Note I normally don't ship features so down to the wire with a release, but this one is very isolated in its impact and I'm going to explicit document it in the release notes and website as a preview since I fully expect we're going to iterate a lot on the objects and commands exposed. From a security perspective, Apple already prompts for permission to control different applications so we're covered, but there is a master kill switch you can put in the config, too.

Mitchell Hashimoto

181,699 просмотров • 4 месяцев назад

I built a wallet app that sends sBTC using bitcoin addresses instead of Stacks addresses. That's layer 2 sats sent from bitcoin address to bitcoin address in seconds for < $0.01 via the Stacks network: ✅Standard bitcoin addresses ✅Standard sign and broadcast semantics ✅Confirmation in seconds ✅Low fees ✅Self-custody ✅Bitcoin finality While this wallet is a prototype that works only with native Segwit addresses and requires or Leather - Grow your Bitcoin for transaction signing, Bitcoin addresses for sBTC (or all Stacks assets) could be adopted natively by any wallets. It doesn't require any changes to the Stacks core network. This address scheme could even be expanded so that fast, easy and cheap layer 2 BTC transactions could also work with legacy addresses. Here's how it works: Bitcoin legacy and native segwit addresses along with Stacks addresses all encode the so-called "hash160" of the user's public key. This means we can convert these two types of bitcoin addresses into a Stacks address and any Stacks address into either a legacy or native segwit bitcoin address. Using bitcoin addresses instead of Stacks addresses allows us to reuse many of the payment standards and QR code formats that have already been developed for bitcoin. It makes sBTC a true layer 2 bitcoin.

I built a wallet app that sends sBTC using bitcoin addresses instead of Stacks addresses. That's layer 2 sats sent from bitcoin address to bitcoin address in seconds for < $0.01 via the Stacks network: ✅Standard bitcoin addresses ✅Standard sign and broadcast semantics ✅Confirmation in seconds ✅Low fees ✅Self-custody ✅Bitcoin finality While this wallet is a prototype that works only with native Segwit addresses and requires or Leather - Grow your Bitcoin for transaction signing, Bitcoin addresses for sBTC (or all Stacks assets) could be adopted natively by any wallets. It doesn't require any changes to the Stacks core network. This address scheme could even be expanded so that fast, easy and cheap layer 2 BTC transactions could also work with legacy addresses. Here's how it works: Bitcoin legacy and native segwit addresses along with Stacks addresses all encode the so-called "hash160" of the user's public key. This means we can convert these two types of bitcoin addresses into a Stacks address and any Stacks address into either a legacy or native segwit bitcoin address. Using bitcoin addresses instead of Stacks addresses allows us to reuse many of the payment standards and QR code formats that have already been developed for bitcoin. It makes sBTC a true layer 2 bitcoin.

Larry Salibra | larry.btc

34,731 просмотров • 1 год назад

we all mourned the loss of Arc. no other browser delivered swipeable spaces + per-space profiles (without spawning new windows). nothing feels truly 120fps smooth and native. Zen is a Firefox wrapper. Helium is just thin shims on Chromium. so I built Tangent built on Chromium (for compatibility) + Rust + GPUI (the engine behind Zed’s legendary performance). - swipeable spaces - different profiles per space in one window - sync across profiles (something even Arc never did) - true 120fps native feel - all the Arc features you loved + more - cross platform foundations from Day 1 - free and open source the browser I would have paid anything for, and yet nobody sold it to me. fast, alive, and built to last. coming soon to devices near you

we all mourned the loss of Arc. no other browser delivered swipeable spaces + per-space profiles (without spawning new windows). nothing feels truly 120fps smooth and native. Zen is a Firefox wrapper. Helium is just thin shims on Chromium. so I built Tangent built on Chromium (for compatibility) + Rust + GPUI (the engine behind Zed’s legendary performance). - swipeable spaces - different profiles per space in one window - sync across profiles (something even Arc never did) - true 120fps native feel - all the Arc features you loved + more - cross platform foundations from Day 1 - free and open source the browser I would have paid anything for, and yet nobody sold it to me. fast, alive, and built to last. coming soon to devices near you

Prithvish ⋅ d4mr

147,040 просмотров • 8 дней назад

I've posed a question: "Does OpenAI have a better pre-train in the back pocket or not?" and looks like the answer from Mark Chen is "Yes" - so we should expect a big response from OpenAI before the end of the year. Mark Chen, OpenAI Head of Research: - "In the last 2 years we've put so much resourcing into, into reasoning and one byproduct of that is you lose a little bit of muscle on pre training and post training." - "In the last six months, Jakub Pachocki and I have done a lot of work to build that muscle back up." - "With all the focus on RL, there's an alpha for us because we think there's so much room left in pre training." - "As a result of these efforts, we've been training much stronger models. And that also gives us a lot of confidence carrying into Gemini 3 and other releases coming this end of the year." So it does look like my assessment was broadly correct and they were neglecting pre-training quite a bit. The good news is that they've spent the last 6 months building that up and the big response shouldn't be too far away.

I've posed a question: "Does OpenAI have a better pre-train in the back pocket or not?" and looks like the answer from Mark Chen is "Yes" - so we should expect a big response from OpenAI before the end of the year. Mark Chen, OpenAI Head of Research: - "In the last 2 years we've put so much resourcing into, into reasoning and one byproduct of that is you lose a little bit of muscle on pre training and post training." - "In the last six months, Jakub Pachocki and I have done a lot of work to build that muscle back up." - "With all the focus on RL, there's an alpha for us because we think there's so much room left in pre training." - "As a result of these efforts, we've been training much stronger models. And that also gives us a lot of confidence carrying into Gemini 3 and other releases coming this end of the year." So it does look like my assessment was broadly correct and they were neglecting pre-training quite a bit. The good news is that they've spent the last 6 months building that up and the big response shouldn't be too far away.

Peter Gostev

84,628 просмотров • 7 месяцев назад