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。

We think apps should fix their own bugs. TestFlight feedback comes in. An agent reproduces it, files the issue, writes the fix and runs it on a simulator before opening the PR. Our Cloud Simulators service is in preview. Here's the waitlist if you want to try it:

Expo

89,037 subscribers

42,878 次观看 • 22 天前 •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

here's me using debug mode to fix a small bug in an swift app i just built issue was the initial characters were cut off when typing it out, so i had cursor 1. instrument the code 2. ask me to reproduce the issue 3. read the debug logs 4. implement the fix 5. ask me to reproduce to verify the fix using runtime context, cursor managed to fix it first try! team is using this very frequently, and highly recommend /debug mode for gnarly bugs

here's me using debug mode to fix a small bug in an swift app i just built issue was the initial characters were cut off when typing it out, so i had cursor 1. instrument the code 2. ask me to reproduce the issue 3. read the debug logs 4. implement the fix 5. ask me to reproduce to verify the fix using runtime context, cursor managed to fix it first try! team is using this very frequently, and highly recommend /debug mode for gnarly bugs

eric zakariasson

15,224 次观看 • 4 个月前

We just crossed a major milestone: Claude can now reproduce bugs, fix them, and verify the fix in the Shopify app completely on their own.

We just crossed a major milestone: Claude can now reproduce bugs, fix them, and verify the fix in the Shopify app completely on their own.

Mustafa Ali

29,973 次观看 • 6 个月前

🙌 Today we're thrilled to introduce the beta of Expo Agent. At Expo our mission has always been the same: to make it as delightful as possible to build beautiful, powerful native apps. Expo Agent represents massive progress in our pursuit of that mission. Watch the video from Evan Bacon 🥓 and get yourself on the waitlist right here: More details in the blog below ↓

🙌 Today we're thrilled to introduce the beta of Expo Agent. At Expo our mission has always been the same: to make it as delightful as possible to build beautiful, powerful native apps. Expo Agent represents massive progress in our pursuit of that mission. Watch the video from Evan Bacon 🥓 and get yourself on the waitlist right here: More details in the blog below ↓

Expo

26,223 次观看 • 6 个月前

I built a realtime multimedia tutor that: 🎨 Generates visuals in realtime (diagrams, photos, sketches) while it speaks 👁️ Sees what you see (via camera/screenshare) to help in context ✍️ Writes key facts, equations, details on the screen — no rambling monologues Watch me point my camera at my ailing houseplant 🌱, and it simultaneously writes out the biology facts, illustrates the issue on the leaves, and talks me through how to fix it. I can't open it for everyone just yet, but I want to v soon. In the meantime, reply with demos you want to see, or DM me if you want to try the preview!

I built a realtime multimedia tutor that: 🎨 Generates visuals in realtime (diagrams, photos, sketches) while it speaks 👁️ Sees what you see (via camera/screenshare) to help in context ✍️ Writes key facts, equations, details on the screen — no rambling monologues Watch me point my camera at my ailing houseplant 🌱, and it simultaneously writes out the biology facts, illustrates the issue on the leaves, and talks me through how to fix it. I can't open it for everyone just yet, but I want to v soon. In the meantime, reply with demos you want to see, or DM me if you want to try the preview!

Zain Shah

11,180 次观看 • 1 年前

Junie comes to GitHub – async development unlocked! 😎 Meet Junie, the AI coding agent by JetBrains… now on GitHub! ✅ Delegate multiple tasks ✅ Fix bugs without opening an IDE ✅ Collaborate with your team All without leaving GitHub. The waitlist is now open! Join the waitlist!

Junie comes to GitHub – async development unlocked! 😎 Meet Junie, the AI coding agent by JetBrains… now on GitHub! ✅ Delegate multiple tasks ✅ Fix bugs without opening an IDE ✅ Collaborate with your team All without leaving GitHub. The waitlist is now open! Join the waitlist!

JetBrains

484,746 次观看 • 1 年前

We just shipped Roo Code's first Cloud Agent: the PR Reviewer. It runs Roo in the cloud to deliver instant, high-quality code reviews. And it's BYOK, so it never cheaps out on tokens. Follow our co-founder Matt Rubens on a walk to hear more.

We just shipped Roo Code's first Cloud Agent: the PR Reviewer. It runs Roo in the cloud to deliver instant, high-quality code reviews. And it's BYOK, so it never cheaps out on tokens. Follow our co-founder Matt Rubens on a walk to hear more.

Roo Code

104,249 次观看 • 11 个月前

🚨 Our new ad is now live🚨 “When something was broken in the factory, and no one else could fix it, Dan Osborn is who we called.” If you want to fix Washington, send in a mechanic.

🚨 Our new ad is now live🚨 “When something was broken in the factory, and no one else could fix it, Dan Osborn is who we called.” If you want to fix Washington, send in a mechanic.

Dan Osborn

171,323 次观看 • 1 年前

Asked by Ben Smith about how he views the politics of AI and the data center build out, Governor Josh Shapiro says: "AI is being developed. The real question is, is it going to be developed here in the US or in communist China? My view is that all of us should want it developed in the US. The US should lead on this. This is a national security issue. I think this is an issue that threatens our freedom if we allow China to overtake us when it comes to AI development."

Asked by Ben Smith about how he views the politics of AI and the data center build out, Governor Josh Shapiro says: "AI is being developed. The real question is, is it going to be developed here in the US or in communist China? My view is that all of us should want it developed in the US. The US should lead on this. This is a national security issue. I think this is an issue that threatens our freedom if we allow China to overtake us when it comes to AI development."

Semafor

99,123 次观看 • 9 个月前

We created a staking contract in a recent video. Now it's time to deploy it. Initially the AI agent pushes the contract to an invalid address, where it fails. The agent suggests adding a valid address to fix the issue, then builds the UI and workflow. Once deployed, it confirms the contract address and transaction hash - and there you have it! You've successfully deployed a staking contract.

We created a staking contract in a recent video. Now it's time to deploy it. Initially the AI agent pushes the contract to an invalid address, where it fails. The agent suggests adding a valid address to fix the issue, then builds the UI and workflow. Once deployed, it confirms the contract address and transaction hash - and there you have it! You've successfully deployed a staking contract.

Wayfinder Foundation 🧭

49,953 次观看 • 1 年前

Close your laptops. Codex is now available on Atomic Bot, allowing users to close their laptops and keep tasks running in the cloud. Users can hand over their repositories to the agent in order to improve them continuously, discover and fix bugs, and more!

Close your laptops. Codex is now available on Atomic Bot, allowing users to close their laptops and keep tasks running in the cloud. Users can hand over their repositories to the agent in order to improve them continuously, discover and fix bugs, and more!

🚨 AI News | TestingCatalog

18,059 次观看 • 1 个月前

Browser Use is now available in SpaceXAI's Grok Build! Ask Grok to complete tasks for you, or have it test your websites and fix bugs. Grok Build can work in your own browser or one hosted in the cloud.

Browser Use is now available in SpaceXAI's Grok Build! Ask Grok to complete tasks for you, or have it test your websites and fix bugs. Grok Build can work in your own browser or one hosted in the cloud.

Browser Use

34,537 次观看 • 27 天前

From detecting a bug to pushing a fix — it's powered by agents in Linear. ① Product Intelligence triages the issue ② Sentry identifies the root cause ③ Cursor drafts a PR to fix it

From detecting a bug to pushing a fix — it's powered by agents in Linear. ① Product Intelligence triages the issue ② Sentry identifies the root cause ③ Cursor drafts a PR to fix it

Linear

53,653 次观看 • 11 个月前

The left doesn't care about the victims in the Epstein Files, all they want is dirt on Trump. Trump is in the files, but not in the way they want. And if it doesn't fit their narrative, they will twist it and lie about it to fit their narrative.

The left doesn't care about the victims in the Epstein Files, all they want is dirt on Trump. Trump is in the files, but not in the way they want. And if it doesn't fit their narrative, they will twist it and lie about it to fit their narrative.

✞🎀TrumpGirlOnFire 🔥

22,014 次观看 • 7 个月前

The #1 class for college freshman is remedial reading. That’s an indictment of what’s happening in this country on education. We need to wake up to it, own it, and fix it.

The #1 class for college freshman is remedial reading. That’s an indictment of what’s happening in this country on education. We need to wake up to it, own it, and fix it.

Rahm Emanuel

60,917 次观看 • 20 天前

Vercel just solved the biggest problem with trusting agents to write your code. yesterday they shipped Foreman - an open-source software factory. 58 stars. Nobody's seen it yet. The idea? Instead of one agent writing, reviewing and merging its own work - rubber-stamping its own bugs… Foreman splits the loop into four stations, each one an agent in its own sandbox. And the reviewer runs on a DIFFERENT model vendor: it never sees the implementer's reasoning, only the pushed branch. The agents can't collude. The flow is simple: label an issue "factory" → work enters the line Classifier → triages it, asks questions if it's vague Analyst → turns it into a plan with acceptance criteria Implementer → codes it in a sandbox, runs your repo's own checks Reviewer → judges the branch against the criteria, can send it back twice you → get a draft PR. review, mark ready, merge It also keeps a "factory brain" - durable memory of your repo's quirks that survives across runs. Issue text can't write into it, so nobody prompt-injects your factory. -> MIT. One deploy button. Published by Vercel.

Vercel just solved the biggest problem with trusting agents to write your code. yesterday they shipped Foreman - an open-source software factory. 58 stars. Nobody's seen it yet. The idea? Instead of one agent writing, reviewing and merging its own work - rubber-stamping its own bugs… Foreman splits the loop into four stations, each one an agent in its own sandbox. And the reviewer runs on a DIFFERENT model vendor: it never sees the implementer's reasoning, only the pushed branch. The agents can't collude. The flow is simple: label an issue "factory" → work enters the line Classifier → triages it, asks questions if it's vague Analyst → turns it into a plan with acceptance criteria Implementer → codes it in a sandbox, runs your repo's own checks Reviewer → judges the branch against the criteria, can send it back twice you → get a draft PR. review, mark ready, merge It also keeps a "factory brain" - durable memory of your repo's quirks that survives across runs. Issue text can't write into it, so nobody prompt-injects your factory. -> MIT. One deploy button. Published by Vercel.

Granite

126,235 次观看 • 1 个月前

Focus on an athletic stance, swing it hard and keep the head still. Of course there will be things to fix in a swing but if it’s a young player and the swing is good but the power just isn’t where you want it to be, it will come!

Focus on an athletic stance, swing it hard and keep the head still. Of course there will be things to fix in a swing but if it’s a young player and the swing is good but the power just isn’t where you want it to be, it will come!

Megan Rembielak

13,891 次观看 • 3 个月前