正在加载视频...

视频加载失败

加载此视频时出现问题。这可能是由于临时网络问题，或视频可能不可用。

Grok Build is able to write code, deploy to a phone on revyl, and look at the screen to check its own work. no human in the loop. watching it edit, hot-reload, and screenshot to verify in real time is genuinely wild.

Anam Hira

1,253 subscribers

10,683 次观看 • 1 个月前 •via X (Twitter)

Anya Rossi• Live Now

Private livecam show

0 条评论

暂无评论

原始帖子的评论将显示在这里

相关视频

Grok Build is absolutely amazing! I just tried it out for the first time. I haven't coded in close to 20 years. I literally have no idea what I'm doing so I had to use Grok to walk me through the process to install and use the tool. I asked it to build me a simple "Thank You Elon Musk" website and it did it in seconds! This is going to completely change everything. Even your grandma will be able to code using Grok Build!

Grok Build is absolutely amazing! I just tried it out for the first time. I haven't coded in close to 20 years. I literally have no idea what I'm doing so I had to use Grok to walk me through the process to install and use the tool. I asked it to build me a simple "Thank You Elon Musk" website and it did it in seconds! This is going to completely change everything. Even your grandma will be able to code using Grok Build!

Adam Lowisz X Meetup 🇺🇸🇵🇱🇪🇺🇬🇧🇺🇦

15,395 次观看 • 2 个月前

real-time token feed is live > watch deployments land in real time > verify deployers and fee recipients > check charts want to launch your own? 4 steps. no code.

real-time token feed is live > watch deployments land in real time > verify deployers and fee recipients > check charts want to launch your own? 4 steps. no code.

deployer

121,623 次观看 • 5 个月前

ANTHROPIC LEAD ENGINEER MAKING $2.3M/YEAR JUST LEAKED A 12-PAGE DOCUMENT - AND GOT FIRED 15 MINUTES AFTER PUBLISHING most developers build loops - but almost every loop breaks in one of five ways, and each failure has a symptom visible from the outside without reading a single line of code > Blind loop - the agent waits for a human to hand it work every morning - automating execution but not discovery > Tangled loop - parallel agents share one directory and overwrite each other parallelism that destroys instead of multiplies > Nodding loop - the agent grades its own work and approves it every time a loop that has never said no to itself is broken > Amnesiac loop - results live only in the context window every morning the system wakes up with no memory of yesterday > Manual loop - no trigger a human presses the button to start it that is not a loop that is a script waiting for a person a real loop finds its own work - remembers what it did has something that can say no never lets two agents touch the same file and fires itself on a timer remove any one of the five - and the loop either breaks or never starts 12 pages that changed how I build agentic systems today

ANTHROPIC LEAD ENGINEER MAKING $2.3M/YEAR JUST LEAKED A 12-PAGE DOCUMENT - AND GOT FIRED 15 MINUTES AFTER PUBLISHING most developers build loops - but almost every loop breaks in one of five ways, and each failure has a symptom visible from the outside without reading a single line of code > Blind loop - the agent waits for a human to hand it work every morning - automating execution but not discovery > Tangled loop - parallel agents share one directory and overwrite each other parallelism that destroys instead of multiplies > Nodding loop - the agent grades its own work and approves it every time a loop that has never said no to itself is broken > Amnesiac loop - results live only in the context window every morning the system wakes up with no memory of yesterday > Manual loop - no trigger a human presses the button to start it that is not a loop that is a script waiting for a person a real loop finds its own work - remembers what it did has something that can say no never lets two agents touch the same file and fires itself on a timer remove any one of the five - and the loop either breaks or never starts 12 pages that changed how I build agentic systems today

Sprytix

153,379 次观看 • 26 天前

ELON: GROK 5 WILL UNDERSTAND REAL TIME VIDEO AND CREATE ITS OWN TOOLS “The quality of the data we are training on with Grok 5 is extraordinary. It is inherently multimodal with text, pictures, video, and audio. It is going to be much better at tool use and in fact at creating tools to be more effective at answering questions and understanding the world. Its vision will be extremely good. It will have real time video, which is fundamentally important." Source: Baron Capital

ELON: GROK 5 WILL UNDERSTAND REAL TIME VIDEO AND CREATE ITS OWN TOOLS “The quality of the data we are training on with Grok 5 is extraordinary. It is inherently multimodal with text, pictures, video, and audio. It is going to be much better at tool use and in fact at creating tools to be more effective at answering questions and understanding the world. Its vision will be extremely good. It will have real time video, which is fundamentally important." Source: Baron Capital

Mario Nawfal

148,015 次观看 • 8 个月前

"The work is done, and here’s the video to prove it." 🎥 Watching these agents run their own browser tests and provide screen recordings of the finished task is a massive win for transparency. It's not just about writing code; it's about closing the feedback loop automatically.

"The work is done, and here’s the video to prove it." 🎥 Watching these agents run their own browser tests and provide screen recordings of the finished task is a massive win for transparency. It's not just about writing code; it's about closing the feedback loop automatically.

Google Antigravity

72,241 次观看 • 5 个月前

CLAUDE CAN NOW TEST ITS OWN CODE IN A REAL BROWSER AND SCREEN RECORD ITSELF DOING IT SO YOU NEVER HAVE TO VERIFY MANUALLY it opens a real browser, catches console errors, confirms network calls, and records every step, so it stops saying "this should work" and starts proving it does.

CLAUDE CAN NOW TEST ITS OWN CODE IN A REAL BROWSER AND SCREEN RECORD ITSELF DOING IT SO YOU NEVER HAVE TO VERIFY MANUALLY it opens a real browser, catches console errors, confirms network calls, and records every step, so it stops saying "this should work" and starts proving it does.

0xMarioNawfal

51,153 次观看 • 1 个月前

the full 12-minute run sped to 80 seconds, watch carnice v2 cycle through plan, terminal probe, todo update, write the report, then read it back to verify, until the loop closes. no edit cuts, no narration, just the model working at 5x time. the rare-bird verify moment lands in the last 20 seconds, write_file then read_file then done. closed loop on consumer hardware, you can watch it happen.

the full 12-minute run sped to 80 seconds, watch carnice v2 cycle through plan, terminal probe, todo update, write the report, then read it back to verify, until the loop closes. no edit cuts, no narration, just the model working at 5x time. the rare-bird verify moment lands in the last 20 seconds, write_file then read_file then done. closed loop on consumer hardware, you can watch it happen.

Sudo su

11,881 次观看 • 2 个月前

Anthropic engineer: "Over 90% of Anthropic engineers use a self-improving agentic loop for coding. The key is to close the loop: give the agent a way to verify and improve its own work" In this 12-minute talk, an Anthropic engineer explains how to build an agent that continuously improves itself. Claude + routines + loops + CLAUDE.md - that's the foundation. Skip Netflix tonight. Save this post!

Anthropic engineer: "Over 90% of Anthropic engineers use a self-improving agentic loop for coding. The key is to close the loop: give the agent a way to verify and improve its own work" In this 12-minute talk, an Anthropic engineer explains how to build an agent that continuously improves itself. Claude + routines + loops + CLAUDE.md - that's the foundation. Skip Netflix tonight. Save this post!

unicode

61,880 次观看 • 1 个月前

Building automations in 10 seconds. Is it really possible? You've heard of no-code automations (useful but takes a while to build) What if you could write text.... And the automation was built on it's own? It's called "text-to-automation" 👇

Building automations in 10 seconds. Is it really possible? You've heard of no-code automations (useful but takes a while to build) What if you could write text.... And the automation was built on it's own? It's called "text-to-automation" 👇

Aadit Sheth

106,150 次观看 • 3 年前

Something cool - had Devin build a React Native app with Expo and test it on my phone in real time AI writes code in the cloud, I scan a QR code, app shows up on my device with hot reload. No local dev environment needed! I can run parallel sessions from anywhere.

Something cool - had Devin build a React Native app with Expo and test it on my phone in real time AI writes code in the cloud, I scan a QR code, app shows up on my device with hot reload. No local dev environment needed! I can run parallel sessions from anywhere.

nader dabit

32,113 次观看 • 4 个月前

The software factory is already here. We're seeing bots write code, bots review it, and humans reduced to dispatching the next tool in the chain. Using 500k+ PRs from Code Review Bench, we looked at one question: can the human leave the loop yet?

The software factory is already here. We're seeing bots write code, bots review it, and humans reduced to dispatching the next tool in the chain. Using 500k+ PRs from Code Review Bench, we looked at one question: can the human leave the loop yet?

Martian

49,102 次观看 • 3 个月前

oh my... Claude Code is evolving You can now build a web app and mobile app at the same time... with Claude Code from a single platform ... > Build iOS App, send to app store > Build web App (New), deploy to the internet w/ 1 click > All apps deploy frontend and backend

oh my... Claude Code is evolving You can now build a web app and mobile app at the same time... with Claude Code from a single platform ... > Build iOS App, send to app store > Build web App (New), deploy to the internet w/ 1 click > All apps deploy frontend and backend

Chorus.com

81,928 次观看 • 6 个月前

I let a loop of AI agents build GTA 6 while I slept. Woke up to a dead Mac and a half walking NPC. Day 8. We're moving the whole game from Godot to Unreal, and the agents kept shipping right through it: - the first NPC walks but no animations - in-game phone now has maps, contacts, and a wallet. Bad news: the Mac died overnight because every agent opened the game at once to screenshot it. Fix was one line in claude.md, only one game or editor open at a time. Agents are back to looping, one at a time. Tomorrow: finish converting the entire repo to Unreal, and work the walk animation so the NPC actually looks real. The loop keeps building the phone apps, and I might pull the map onto the phone so the whole thing feels seamless. One catch: the licensed Unreal assets can't be shared publicly, so that part stays in a private build.

I let a loop of AI agents build GTA 6 while I slept. Woke up to a dead Mac and a half walking NPC. Day 8. We're moving the whole game from Godot to Unreal, and the agents kept shipping right through it: - the first NPC walks but no animations - in-game phone now has maps, contacts, and a wallet. Bad news: the Mac died overnight because every agent opened the game at once to screenshot it. Fix was one line in claude.md, only one game or editor open at a time. Agents are back to looping, one at a time. Tomorrow: finish converting the entire repo to Unreal, and work the walk animation so the NPC actually looks real. The loop keeps building the phone apps, and I might pull the map onto the phone so the whole thing feels seamless. One catch: the licensed Unreal assets can't be shared publicly, so that part stays in a private build.

Ziwen

290,991 次观看 • 1 个月前

First look at Grok Build by xAI, this time as a CLI tool running directly in the terminal. This is clearly positioned as a competitor to Claude Code, bringing agentic coding workflows into the command line with xAI’s own model stack behind it.

First look at Grok Build by xAI, this time as a CLI tool running directly in the terminal. This is clearly positioned as a competitor to Claude Code, bringing agentic coding workflows into the command line with xAI’s own model stack behind it.

Mark Kretschmann

36,320 次观看 • 2 个月前

Jenny Wen, head of design for Claude at Anthropic: "the design process is dead." what replaces it runs on machine-readable design systems In a 1-hour conversation, Jenny Wen breaks down why the discovery -> mock -> iterate loop is dying and what designers do instead. design system -> Claude Code -> every screen fixed at once, not one at a time i rebuilt the same 10-screen dashboard twice: ~6 hours of restyling by hand vs ~40 minutes when the fix lived in the system. how to build that system and hand it to Claude Code is in the article below.

Jenny Wen, head of design for Claude at Anthropic: "the design process is dead." what replaces it runs on machine-readable design systems In a 1-hour conversation, Jenny Wen breaks down why the discovery -> mock -> iterate loop is dying and what designers do instead. design system -> Claude Code -> every screen fixed at once, not one at a time i rebuilt the same 10-screen dashboard twice: ~6 hours of restyling by hand vs ~40 minutes when the fix lived in the system. how to build that system and hand it to Claude Code is in the article below.

Mnimiy

180,395 次观看 • 1 个月前

Code Blocks in ChatGPT got more interactive. Write, edit, and preview your code, all in one place: • Create and preview diagrams and mini apps in chat • Review code in split-screen views • Make changes in full-screen view We’d love to see what you’ll build.

Code Blocks in ChatGPT got more interactive. Write, edit, and preview your code, all in one place: • Create and preview diagrams and mini apps in chat • Review code in split-screen views • Make changes in full-screen view We’d love to see what you’ll build.

OpenAI Developers

426,831 次观看 • 5 个月前

The new Screenshot to Code from Vercel v0 is insane. I just took a screenshot of a pricing table and it was converted into code using AI in seconds! It even outputs the code and allows you to modify any specific parts.

The new Screenshot to Code from Vercel v0 is insane. I just took a screenshot of a pricing table and it was converted into code using AI in seconds! It even outputs the code and allows you to modify any specific parts.

Alvaro Cintas

378,020 次观看 • 2 年前

i watched gemma 4 12b build something genuinely impressive today, and then loop itself to death right in front of me. the full run is in the video, sped up but completely uncut, watch it to the end and you will catch the exact moment it stops building and starts looping right in the middle of the work. the task was clean, build a single file gravity simulator, n-body physics, orbits, collisions, running locally on one 3090 through an agent. and for ten minutes it was a joy to watch. it reached for a symplectic integrator on its own, the correct one, the kind that keeps orbits stable instead of spiralling out. real gravity with softening, proper orbital velocities, momentum conserved on collision. the physics was right. the thing actually worked. then on the very last step, writing a few tests to prove its own code, it fell into a loop. not a crash, a loop. it started repeating itself and would not stop. ten more minutes, thirty four thousand tokens into a single answer, the same fragments over and over, until i killed it myself. so it's not that gemma can't code. it did the hard part beautifully. it cannot finish. it cannot hold a long task together without unravelling, and finishing is the entire job in agentic work. here's the part that stings. i run this exact task, same harness, same card, on the chinese open models, qwen especially, and i never see this. they build it, they test it, they stop. every single time. google has the raw capability, you can see it sitting right there in the code, and then the model loops itself to death on a task a 27b from alibaba finishes clean. open weights, apache 2.0, so much to love on paper. i just need it to know when to stop talking.

i watched gemma 4 12b build something genuinely impressive today, and then loop itself to death right in front of me. the full run is in the video, sped up but completely uncut, watch it to the end and you will catch the exact moment it stops building and starts looping right in the middle of the work. the task was clean, build a single file gravity simulator, n-body physics, orbits, collisions, running locally on one 3090 through an agent. and for ten minutes it was a joy to watch. it reached for a symplectic integrator on its own, the correct one, the kind that keeps orbits stable instead of spiralling out. real gravity with softening, proper orbital velocities, momentum conserved on collision. the physics was right. the thing actually worked. then on the very last step, writing a few tests to prove its own code, it fell into a loop. not a crash, a loop. it started repeating itself and would not stop. ten more minutes, thirty four thousand tokens into a single answer, the same fragments over and over, until i killed it myself. so it's not that gemma can't code. it did the hard part beautifully. it cannot finish. it cannot hold a long task together without unravelling, and finishing is the entire job in agentic work. here's the part that stings. i run this exact task, same harness, same card, on the chinese open models, qwen especially, and i never see this. they build it, they test it, they stop. every single time. google has the raw capability, you can see it sitting right there in the code, and then the model loops itself to death on a task a 27b from alibaba finishes clean. open weights, apache 2.0, so much to love on paper. i just need it to know when to stop talking.

Sudo su

39,574 次观看 • 1 个月前

Want to build ENTIRE front ends without knowing how to code? Describe what you want your front end to look like, and OpenUI will build it in real time! Super impressive. Here's the tutorial:

Want to build ENTIRE front ends without knowing how to code? Describe what you want your front end to look like, and OpenUI will build it in real time! Super impressive. Here's the tutorial:

Matthew Berman

90,635 次观看 • 2 年前