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

My favorite cmux feature is Cmd+Shift+U. I have 17 workspaces open right now, each running an agent. I used to click through tabs and macOS system-wide notifications to figure out what completed. But with cmux, I can just "Cmd+Shift+U" Cmd+Shift+U jumps to the newest unread notification. In practice that... show more

Lawrence Chen

4,956 subscribers

28,517 просмотров • 6 месяцев назад •via X (Twitter)

Anya Rossi• Live Now

Private livecam show

Комментарии: 0

Нет доступных комментариев

Здесь появятся комментарии из оригинального поста

Похожие видео

I know this post is a little late but I was blessed enough to spend ur whole birthday with U and we’re still celebrating 🍾🥂💃🕺 Our bond is so perfectly matched in the most organic way. I kno it was God that brought us 2gether. If ppl only knew how big of a role u play in my life and in my career. If they only knew ur a big part of the reason the beehive is getting new music right now. U are my motivation and that voice that is always cheering me on. Ur so intelligent and such a boss. If they only knew the things we figure out 2gether, how we can talk with our eyes and be on the same page. How we are each others rock, the late night talks, the gut wrenching laughs we share, the arguments, the debates. U get on my nerves sometimes 🙄 😩 but it also brings me great pleasure to annoy u cause I’m annoying 👋 Hi Even after I annoy u, u always give me the biggest smile. Which if anyone knows u, they know that u barely do and that’s why it makes me so happy to annoy u 😹 😻 It’s so weird how we became so close because it happened out of nowhere but I’m really proud of what we’re building and most of all the unconditional love we have for each other. Ur a sweet gangsta and I love it! I always want the best for u and I wanna see u go all the way to the top where u belong. U deserve it. My twinn, my bestfrennn. So proud to call u my artist. I Love u 4 Ever @realtayybrown 🫶❤️❤️❤️ HBD month!

I know this post is a little late but I was blessed enough to spend ur whole birthday with U and we’re still celebrating 🍾🥂💃🕺 Our bond is so perfectly matched in the most organic way. I kno it was God that brought us 2gether. If ppl only knew how big of a role u play in my life and in my career. If they only knew ur a big part of the reason the beehive is getting new music right now. U are my motivation and that voice that is always cheering me on. Ur so intelligent and such a boss. If they only knew the things we figure out 2gether, how we can talk with our eyes and be on the same page. How we are each others rock, the late night talks, the gut wrenching laughs we share, the arguments, the debates. U get on my nerves sometimes 🙄 😩 but it also brings me great pleasure to annoy u cause I’m annoying 👋 Hi Even after I annoy u, u always give me the biggest smile. Which if anyone knows u, they know that u barely do and that’s why it makes me so happy to annoy u 😹 😻 It’s so weird how we became so close because it happened out of nowhere but I’m really proud of what we’re building and most of all the unconditional love we have for each other. Ur a sweet gangsta and I love it! I always want the best for u and I wanna see u go all the way to the top where u belong. U deserve it. My twinn, my bestfrennn. So proud to call u my artist. I Love u 4 Ever @realtayybrown 🫶❤️❤️❤️ HBD month!

Lil' Kim

1,073,117 просмотров • 2 лет назад

Your projects now share one window in Air. Start an agent in the backend, switch to the frontend while it runs, then jump to finished work elsewhere. And if you group tasks by status, it's easy to see what needs attention, what’s running, and what’s ready to review.

Your projects now share one window in Air. Start an agent in the backend, switch to the frontend while it runs, then jump to finished work elsewhere. And if you group tasks by status, it's easy to see what needs attention, what’s running, and what’s ready to review.

JetBrains Air

21,761 просмотров • 1 месяц назад

Gratitude is one of the fastest ways to shift your energy and align with what you want. 💫 When you write your desires as if they’ve already happened, you move from hoping… to believing. From wishing… to receiving. Feel the joy. Feel the relief. Feel the gratitude as though it’s already yours. That emotional shift is powerful—and it begins attracting your desire into reality. 🌟 If you want to deepen this daily practice and truly align with abundance, Countdown to Riches is now available to guide you step by step. Secure your copy today 👉 Finish this sentence — “I am so happy and grateful now that I have…” ✨

Gratitude is one of the fastest ways to shift your energy and align with what you want. 💫 When you write your desires as if they’ve already happened, you move from hoping… to believing. From wishing… to receiving. Feel the joy. Feel the relief. Feel the gratitude as though it’s already yours. That emotional shift is powerful—and it begins attracting your desire into reality. 🌟 If you want to deepen this daily practice and truly align with abundance, Countdown to Riches is now available to guide you step by step. Secure your copy today 👉 Finish this sentence — “I am so happy and grateful now that I have…” ✨

The Secret

17,306 просмотров • 7 месяцев назад

Out of sheer frustration ... I decided to vibe code my own tile map editor to see if it can help with making my agent skills be able to build better levels. It also proves that the agent skill is sufficiently good enough to know how to read the tilemaps - just bad at level design. So maybe I just need to build a level design skill.

Out of sheer frustration ... I decided to vibe code my own tile map editor to see if it can help with making my agent skills be able to build better levels. It also proves that the agent skill is sufficiently good enough to know how to read the tilemaps - just bad at level design. So maybe I just need to build a level design skill.

Chong-U

37,202 просмотров • 8 месяцев назад

💬 why isn't the bed against the wall? 🐥 with the layout of this room, it actually looked strange if it's place against the wall, so i just put it in the middle. and when u open that window, the view outside is pretty

💬 why isn't the bed against the wall? 🐥 with the layout of this room, it actually looked strange if it's place against the wall, so i just put it in the middle. and when u open that window, the view outside is pretty

기쁨

17,539 просмотров • 4 месяцев назад

Jared McCain says he wants to get this photo framed. I asked him where he wants to put it: “Maybe like right next to my TV in the living room. Or maybe right above my bed, so right when I wake up I can just look at that and it reminds me that this is where I’m supposed to be.”

Jared McCain says he wants to get this photo framed. I asked him where he wants to put it: “Maybe like right next to my TV in the living room. Or maybe right above my bed, so right when I wake up I can just look at that and it reminds me that this is where I’m supposed to be.”

Justin Martinez

153,749 просмотров • 5 месяцев назад

I tried Hedra Agent by Hedra to see if one conversation could replace the usual mess of switching models, rewriting prompts, and juggling tools. So I started with a simple idea, Hedra Agent: - Selected the right models on its own - Generated refined visuals - Suggested multiple stylistic directions - Then turned the chosen frames into a cohesive video All within the same conversation while remembering every detail we discussed. I was able to shift the mood, adjust the lighting, refine the composition, explore different angles, and even adapt the format simply by giving natural feedback. I did not have to restart or rebuild anything from scratch. The Agent handled the workflow from idea to finished, platform-ready content. What stood out was not just the output quality, but also the continuity. Instead of operating tools, it felt like collaborating with a system that understands context and builds with you step by step. Check how it works 👇🏻

I tried Hedra Agent by Hedra to see if one conversation could replace the usual mess of switching models, rewriting prompts, and juggling tools. So I started with a simple idea, Hedra Agent: - Selected the right models on its own - Generated refined visuals - Suggested multiple stylistic directions - Then turned the chosen frames into a cohesive video All within the same conversation while remembering every detail we discussed. I was able to shift the mood, adjust the lighting, refine the composition, explore different angles, and even adapt the format simply by giving natural feedback. I did not have to restart or rebuild anything from scratch. The Agent handled the workflow from idea to finished, platform-ready content. What stood out was not just the output quality, but also the continuity. Instead of operating tools, it felt like collaborating with a system that understands context and builds with you step by step. Check how it works 👇🏻

Amira Zairi

31,593 просмотров • 7 месяцев назад

🚨 one person can now do the work of an entire creative team. i just tested it on a real one. a friend needed an ad for his brand, so I opened the new Runway Agent 2.0 to try it out. here's how it went: → it generated the music and the key image first, so I could approve the direction → once I gave the ok, it built the full video around it → and when something was off, i changed just that one piece, without redoing the rest one prompt, and I had the ad we needed, work that used to take weeks. this is what it made 👇 if you want to try it → · 30% off 3 months with code RUNWAYAGENT — made with Runway · #MadeWithRunway · #ad

brenz.

28,770 просмотров • 3 месяцев назад

Own your personal agent, folks. Just built my own little personal agent with Pi's Pi Durable. I wanted to see how quickly I could build an OpenAI dots clone with open-source tools. I am amazed at how quickly I got this off the ground. It's proactive. It keeps working when you're not watching. It remembers you, runs jobs on a schedule, waits for your approval, and uses its own computer. Pi Durable makes that possible. Every step is checkpointed. I can kill the process mid-task, and My Pi picks up right where it left off. Memory lives in durable documents. What My Pi learns about me in one Space survives a crash and carries over to every other Space. Approvals are durable too. It also has its own computer. Each Space gets a full Linux desktop that My Pi controls with screenshots, mouse, and keyboard. The model runs through OpenRouter, so I can swap models without changing anything else. That's all configurable however you like it. If you've been wanting your own personal agent, now is a great time to build one. I am building this as an experimental ground where I can test new ideas and experiment deeply with proactive personal agents. But I plan to open-source it after testing it a bit and adding more interesting primitives. The goal is to make it customizable and easy to build on, so others can experiment with their own personal agent functionalities.

Own your personal agent, folks. Just built my own little personal agent with Pi's Pi Durable. I wanted to see how quickly I could build an OpenAI dots clone with open-source tools. I am amazed at how quickly I got this off the ground. It's proactive. It keeps working when you're not watching. It remembers you, runs jobs on a schedule, waits for your approval, and uses its own computer. Pi Durable makes that possible. Every step is checkpointed. I can kill the process mid-task, and My Pi picks up right where it left off. Memory lives in durable documents. What My Pi learns about me in one Space survives a crash and carries over to every other Space. Approvals are durable too. It also has its own computer. Each Space gets a full Linux desktop that My Pi controls with screenshots, mouse, and keyboard. The model runs through OpenRouter, so I can swap models without changing anything else. That's all configurable however you like it. If you've been wanting your own personal agent, now is a great time to build one. I am building this as an experimental ground where I can test new ideas and experiment deeply with proactive personal agents. But I plan to open-source it after testing it a bit and adding more interesting primitives. The goal is to make it customizable and easy to build on, so others can experiment with their own personal agent functionalities.

elvis

33,240 просмотров • 2 дней назад

So last night at the movies, I got a notification that my right tire pressure was low, almost flat. I feared that someone had slashed it, but after the movie was done, went outside to check. We found a nail in the tire immediately and I was so happy that I used my referral credits just last week to purchase a tire air compressor in the Tesla shop. I had credits that were going to expire and I figured while I might as well get some safety related things to put in my car since I’m having a baby soon and immediately had a use for it!! This thing works amazingly. I just thought that the timing was so serendipitous and wanted to share. Someone on X recommended I get one for my trunk and so thank you, great product!

So last night at the movies, I got a notification that my right tire pressure was low, almost flat. I feared that someone had slashed it, but after the movie was done, went outside to check. We found a nail in the tire immediately and I was so happy that I used my referral credits just last week to purchase a tire air compressor in the Tesla shop. I had credits that were going to expire and I figured while I might as well get some safety related things to put in my car since I’m having a baby soon and immediately had a use for it!! This thing works amazingly. I just thought that the timing was so serendipitous and wanted to share. Someone on X recommended I get one for my trunk and so thank you, great product!

Ellie in Space 🚀💫

84,963 просмотров • 4 месяцев назад

I STOPPED REVIEWING MY OWN AGENT, SOMETHING ELSE DOES IT NOW I used to read every diff it produced and approve most of them, because an agent grading itself always says the work is good. -> Now a second model with different instructions tries to break the work first, and I only read what survived. Here is what is actually in the folder that took over the night shift: • the brief > CONTRACT.md -- what it may touch, and what it may never touch. > VISION.md -- the destination, so turn 47 still knows why it started. • the gate > judge/ -- a different model, never the one that wrote the code. > break-it.md -- it opens the page, clicks, screenshots, reports back. > -- no opinion, just zero or non-zero. > shift.yml -- 03:30 every night, laptop closed. • the memory > receipts/ -- one folder per night, dated and graded. > STATE.md -- where it stopped and what it escalated. > lessons.log -- the flaky test, written down once instead of rediscovered weekly. • the brakes > caps.json -- turn limit, retry limit, spend limit. > -- written on day one, used never. The generator decides what your loop can produce -> The judge decides what it refuses to produce. One of those is the part everyone builds -> The other is why most loops quietly fail. Bookmark it & Read Full breakdown below ↓

I STOPPED REVIEWING MY OWN AGENT, SOMETHING ELSE DOES IT NOW I used to read every diff it produced and approve most of them, because an agent grading itself always says the work is good. -> Now a second model with different instructions tries to break the work first, and I only read what survived. Here is what is actually in the folder that took over the night shift: • the brief > CONTRACT.md -- what it may touch, and what it may never touch. > VISION.md -- the destination, so turn 47 still knows why it started. • the gate > judge/ -- a different model, never the one that wrote the code. > break-it.md -- it opens the page, clicks, screenshots, reports back. > -- no opinion, just zero or non-zero. > shift.yml -- 03:30 every night, laptop closed. • the memory > receipts/ -- one folder per night, dated and graded. > STATE.md -- where it stopped and what it escalated. > lessons.log -- the flaky test, written down once instead of rediscovered weekly. • the brakes > caps.json -- turn limit, retry limit, spend limit. > -- written on day one, used never. The generator decides what your loop can produce -> The judge decides what it refuses to produce. One of those is the part everyone builds -> The other is why most loops quietly fail. Bookmark it & Read Full breakdown below ↓

slash1s

37,556 просмотров • 2 месяцев назад

I understand it now. The defense has multiple opportunities to effect your green window before you release the ball. Gather, Mid Air, Release. So you have to 100% fill the meter to leave no room for contest error. Don't try to get the meter in the green window if it's large, because that can/will change. Try to COMPLETELY fill the meter, so that if the window does change, it'll still be 100% full, resulting in a Green (I think).

I understand it now. The defense has multiple opportunities to effect your green window before you release the ball. Gather, Mid Air, Release. So you have to 100% fill the meter to leave no room for contest error. Don't try to get the meter in the green window if it's large, because that can/will change. Try to COMPLETELY fill the meter, so that if the window does change, it'll still be 100% full, resulting in a Green (I think).

BlaqKobra 🐍

202,123 просмотров • 1 год назад

[#Jinyoung #진영 박진영 #GOT7] If you were to recommend a GOT7 song that matches today's vibe? 🍑 GOT7's OUT THE DOOR, written by #Mark. I really like that song, so I still listen to it often. It's exactly the kind of vibe that comes to mind. When heading to a schedule, I think 'Wouldn't it feel so refreshing' if i roll the window down a bit and listen to that song.

[#Jinyoung #진영 박진영 #GOT7] If you were to recommend a GOT7 song that matches today's vibe? 🍑 GOT7's OUT THE DOOR, written by #Mark. I really like that song, so I still listen to it often. It's exactly the kind of vibe that comes to mind. When heading to a schedule, I think 'Wouldn't it feel so refreshing' if i roll the window down a bit and listen to that song.

𝐣𝐨𝐲𝐜𝐞

77,071 просмотров • 1 год назад

Another feature that appears to have been snuck in that I had previously requested and will CONSTANTLY be making use of: NEUTRAL-POINT OFFSET! Now, when my model is moved to the side and rotated towards the game, it's no longer locked towards facing left if I look to the right!

Another feature that appears to have been snuck in that I had previously requested and will CONSTANTLY be making use of: NEUTRAL-POINT OFFSET! Now, when my model is moved to the side and rotated towards the game, it's no longer locked towards facing left if I look to the right!

Nyanko Pankotanko 🐱🍞🎀 babiyumeEN

36,092 просмотров • 1 год назад

Seems like Visual Studio Code is starting to tell you: your agent primitives need to move. There is now a new migration banner in the Chat panel, and it is part of a much bigger change happening under the hood: the move from the old Local harness to the new Agent Host architecture built around AHP. This is not just about moving where an agent runs. The old model was very VS Code-centric: prompts, custom agents, instructions and skills could live in VS Code-specific locations and the agent runtime lived inside the extension host. The new Agent Host separates the agent runtime from the editor. Sessions can keep running when the window closes, be shared across VS Code windows, run remotely, and support different harnesses such as Copilot, CLI and Copilot Desktop App through a common session layer. And that means some of our primitives need to move too. Prompt files are being deprecated for Agent Host and migrated to Skills. User-level agents and instructions that lived in VS Code profile storage need to move to harness-supported locations. Even the old location settings are being deprecated. The new migration experience can detect these things and guide you through moving or converting them, while keeping the originals unless you explicitly remove them. The new banner is basically the first visible sign that this migration is becoming a real product workflow. Basically telling us - it's time to move on!!!! If you have accumulated a lot of prompts, custom agents, instructions and skills over the last year, now is probably a good time to understand where they actually live and which harness owns them. To summarize the shift - it isn't just: VS Code Chat → Agent Host It is: VS Code-specific primitives → harness-native primitives. And I think this is going to become increasingly important as agents stop being features inside an IDE and become runtimes that multiple clients can connect to. Go run your migrations now 🏃‍♀️

Oren Melamed

29,753 просмотров • 7 дней назад

Just a simple reminder to GTFOutside. ⛰️ It always provides that energy shift... Bonus points if you can read my mug 😛 And I don’t know what it is, but there’s just something about moss that makes me abnormally happy 🪵 Anyone else? #gtfoutside #earnyourfreedom #camping #nature

Just a simple reminder to GTFOutside. ⛰️ It always provides that energy shift... Bonus points if you can read my mug 😛 And I don’t know what it is, but there’s just something about moss that makes me abnormally happy 🪵 Anyone else? #gtfoutside #earnyourfreedom #camping #nature

Janna Breslin

18,335 просмотров • 1 год назад

🚨 JD VANCE JUST NOW ON 2028: "The way I make decisions...I don't plot things out. I make the decisions that are right in front of me. I try to do as well as I can. And then I figure out when I've got to make a new decision. Because I don't have to make that decision." "I just haven't thought about it that much."

🚨 JD VANCE JUST NOW ON 2028: "The way I make decisions...I don't plot things out. I make the decisions that are right in front of me. I try to do as well as I can. And then I figure out when I've got to make a new decision. Because I don't have to make that decision." "I just haven't thought about it that much."

Eric Daugherty

42,691 просмотров • 3 месяцев назад