Video yükleniyor...

Video Yüklenemedi

Bu video yüklenirken bir sorun oluştu. Bu geçici bir ağ sorunundan kaynaklanıyor olabilir veya video kullanılamıyor olabilir.

Ana Sayfaya Dön

Everyone expected GPT-5 to be a massive leap. But coding accuracy sits around 60% on SWE... meaning even the “best” model still ships bugs. So how do you vibe-code in 2025? One tool caught my eye: They rebuilt a Cursor app inside Cursor using their MCP to test, fix... show more

Eyisha Zyer

126,160 subscribers

54,968 görüntüleme • 1 yıl önce •via X (Twitter)

Bilim & Teknoloji Eğitim

Anya Rossi• Live Now

Private livecam show

0 Yorum

Yorum bulunmuyor

Orijinal gönderinin yorumları burada görünecek

Benzer Videolar

Write 100x better code using AI (for free!) Install the Codacy extension (VSCode, Cursor, WindSurf). This will install an MCP Server locally on your computer. Your coding copilot will use this server with the Codacy CLI to check every line of code it generates. The way this works is pretty awesome (assuming you are using Cursor): 1. You ask Cursor to generate some code 2. Cursor writes the code 3. Cursor then calls Codacy's MCP Server to check it 4. The MCP Server will use the Codacy CLI to find any issues 5. Cursor will fix the issues and call the MCP server again 6. When the code passes all checks, you are done Level of effort on your side: literally zero! Code quality and security because of this: 100x better! Codacy has been doing this for a long, long time, and their Guardrails MCP Server checks for a lot of potential issues: • Security issues • Quality standards • Pattern violations • Linting issues You can see more information about the extension here: I recorded a quick video to show you how it works. Thanks to the Codacy team for helping me set up everything, answering my 1,000 questions, and collaborating with me on this post.

Write 100x better code using AI (for free!) Install the Codacy extension (VSCode, Cursor, WindSurf). This will install an MCP Server locally on your computer. Your coding copilot will use this server with the Codacy CLI to check every line of code it generates. The way this works is pretty awesome (assuming you are using Cursor): 1. You ask Cursor to generate some code 2. Cursor writes the code 3. Cursor then calls Codacy's MCP Server to check it 4. The MCP Server will use the Codacy CLI to find any issues 5. Cursor will fix the issues and call the MCP server again 6. When the code passes all checks, you are done Level of effort on your side: literally zero! Code quality and security because of this: 100x better! Codacy has been doing this for a long, long time, and their Guardrails MCP Server checks for a lot of potential issues: • Security issues • Quality standards • Pattern violations • Linting issues You can see more information about the extension here: I recorded a quick video to show you how it works. Thanks to the Codacy team for helping me set up everything, answering my 1,000 questions, and collaborating with me on this post.

Santiago

63,316 görüntüleme • 1 yıl önce

I BUILT A CURSOR WRAPPER: USING CURSOR WITHOUT WRITING A SINGLE LINE OF CODE FULL VIDEO BELOW: I've been talking to hundreds of people who refuse to try cursor because of how scary the interface is. And fair enough. Terminal, Composer, Agent, Commands... It can be scary. This is why people are using other web based tools to create apps. Which is awesome! But after about 12 prompts, they seem to stop working effectively. Meanwhile, with Cursor you can create MASSIVE projects without coding perfectly fine, for days or weeks. So I got some ideas. I took it upon myself to build a new front end to Cursor, using Cursor without writing one line of code. 00:00 - INTRO 01:29 - LET'S START BY ASKING COMPOSER 15:01 - TESTING THE APP

I BUILT A CURSOR WRAPPER: USING CURSOR WITHOUT WRITING A SINGLE LINE OF CODE FULL VIDEO BELOW: I've been talking to hundreds of people who refuse to try cursor because of how scary the interface is. And fair enough. Terminal, Composer, Agent, Commands... It can be scary. This is why people are using other web based tools to create apps. Which is awesome! But after about 12 prompts, they seem to stop working effectively. Meanwhile, with Cursor you can create MASSIVE projects without coding perfectly fine, for days or weeks. So I got some ideas. I took it upon myself to build a new front end to Cursor, using Cursor without writing one line of code. 00:00 - INTRO 01:29 - LET'S START BY ASKING COMPOSER 15:01 - TESTING THE APP

Riley Brown

166,419 görüntüleme • 1 yıl önce

Your coding agent can run all night. It still can't tell if what it built actually works. Today we're open-sourcing the TestSprite CLl (Apache-2.0) A tool your agent calls on its own to test your app end-to-end like a real user, fix what broke, and re-check everything it ever got right. It's the same engine 100,000+ teams already use. We proved it in public, on a public leaderboard: Most correct app on the board:89% Built by the cheapest model in the field At half the cost of the priciest one You no longer need the biggest, most expensive model to ship software you can trust. Setup is 2 commands: npm install -g @testsprite/testsprite-cli testsprite init That's the last command you'll ever type - from there, your agent runs the tests itself.

Your coding agent can run all night. It still can't tell if what it built actually works. Today we're open-sourcing the TestSprite CLl (Apache-2.0) A tool your agent calls on its own to test your app end-to-end like a real user, fix what broke, and re-check everything it ever got right. It's the same engine 100,000+ teams already use. We proved it in public, on a public leaderboard: Most correct app on the board:89% Built by the cheapest model in the field At half the cost of the priciest one You no longer need the biggest, most expensive model to ship software you can trust. Setup is 2 commands: npm install -g @testsprite/testsprite-cli testsprite init That's the last command you'll ever type - from there, your agent runs the tests itself.

TestSprite

1,042,568 görüntüleme • 3 ay önce

My AI-built saas is finally live! Here’s about my AI-powered coding journey looked like: ~Started with 300 requests on for frontend + Supabase - Lovable got stuck few times, so took my code to cursor. ~741 fast requests on Cursor Pro for features + Stripe -2 months to build MVP. -Stripe integration was the hardest 😅 -MCP made it faster, supabase, stripe and Browser tools MCP's were super helpful. -Needed dev help to fix a web hook issue Still some bugs, but managed to make it live via vercel. Comment or DM if you have any specific questions

My AI-built saas is finally live! Here’s about my AI-powered coding journey looked like: ~Started with 300 requests on for frontend + Supabase - Lovable got stuck few times, so took my code to cursor. ~741 fast requests on Cursor Pro for features + Stripe -2 months to build MVP. -Stripe integration was the hardest 😅 -MCP made it faster, supabase, stripe and Browser tools MCP's were super helpful. -Needed dev help to fix a web hook issue Still some bugs, but managed to make it live via vercel. Comment or DM if you have any specific questions

Deepak Mehta

51,658 görüntüleme • 1 yıl önce

We added a device tool bar to the Codex in-app browser, so it's easier to build and test responsive apps! Now, you can have Codex test your app in different dimensions, so it can fix bugs & improve UI for every device. Just click the 3 dots on the right of the URL bar to use it! As part of this change, we also: - improved the speed of browser use (~30% in my vibe testing) - tightened the animation of the cursor - added a way to hide the composer in full screen mode - fixed a few bugs for browser use in Windows Oliver Tepman and John Nastos cooked on this one! Try it out and let us know what you think!

We added a device tool bar to the Codex in-app browser, so it's easier to build and test responsive apps! Now, you can have Codex test your app in different dimensions, so it can fix bugs & improve UI for every device. Just click the 3 dots on the right of the URL bar to use it! As part of this change, we also: - improved the speed of browser use (~30% in my vibe testing) - tightened the animation of the cursor - added a way to hide the composer in full screen mode - fixed a few bugs for browser use in Windows Oliver Tepman and John Nastos cooked on this one! Try it out and let us know what you think!

James Sun

148,546 görüntüleme • 5 ay önce

"I built a $250,000 SaaS in 4 months with AI and barely knew how to code." I'm starting to think that a coding ide like cursor/windsurf can become the everything app for creators this custom mode wrote a linkedin post that reads better than tools charging $50+ a month it can do it's own research using web searches or using the brave mcp with a free api key it's not hard to imagine that I could also hook this up to an mcp to create posts on linkedin and have my publishing schedule managed from a json file inside cursor yes, linkedin is cringe, but this is just the beginning of what will be possible soon i'm not gonna say that mcp is "wild" or "this changes everything" but it's quite exciting to see how this is going to be used

"I built a $250,000 SaaS in 4 months with AI and barely knew how to code." I'm starting to think that a coding ide like cursor/windsurf can become the everything app for creators this custom mode wrote a linkedin post that reads better than tools charging $50+ a month it can do it's own research using web searches or using the brave mcp with a free api key it's not hard to imagine that I could also hook this up to an mcp to create posts on linkedin and have my publishing schedule managed from a json file inside cursor yes, linkedin is cringe, but this is just the beginning of what will be possible soon i'm not gonna say that mcp is "wild" or "this changes everything" but it's quite exciting to see how this is going to be used

Ian Nuttall

25,659 görüntüleme • 1 yıl önce

Battle of the new coding models: Cursor vs Cognition They both make big claims being near the frontier - how well do they pass the Golden Gate Bridge test? I've included 5x non-cherry picked generations from each, followed by examples from pre-release test of Gemini 3 Pro, GPT-5 and Sonnet 4.5. Generations are mostly one shot, but each had errors twice, which it then fixed in the next generation. My impressions: - Both are clearly way behind the frontier - Between the two, Windsurf's SWE-1.5 is a winner for me - no huge errors like two parts of the bridge are the wrong way round - But SWE-1.5 generations were quite low-fi and Cursor's composer did have some better generations - Overall GPT-5 seems like the best model around on these tests, and Gemini 3 Pro seems to have a lot of potential Music via Suno

Battle of the new coding models: Cursor vs Cognition They both make big claims being near the frontier - how well do they pass the Golden Gate Bridge test? I've included 5x non-cherry picked generations from each, followed by examples from pre-release test of Gemini 3 Pro, GPT-5 and Sonnet 4.5. Generations are mostly one shot, but each had errors twice, which it then fixed in the next generation. My impressions: - Both are clearly way behind the frontier - Between the two, Windsurf's SWE-1.5 is a winner for me - no huge errors like two parts of the bridge are the wrong way round - But SWE-1.5 generations were quite low-fi and Cursor's composer did have some better generations - Overall GPT-5 seems like the best model around on these tests, and Gemini 3 Pro seems to have a lot of potential Music via Suno

Peter Gostev

23,583 görüntüleme • 11 ay önce

The future of product management looks a lot like Zevi Arnovitz Zevi is an IC PM at Meta, has no technical background—is scared to even look at code—but has taught himself how to use Cursor and Claude Code to build significant and real product. He's developed his own very powerful Cursor workflow that allows him to quickly add his ideas to Linear, develop a plan using Claude Code, build it within Cursor, and then have different LLMs review his code. Zevi's engineers at Meta ask him to teach them how he does what he does, and I haven’t stopped thinking about this conversation since we had it. Everyone needs to pay close attention to what AI us unlocking for non-technical people. We discuss: 🔸 The complete AI workflow that lets non-technical people build in Cursor 🔸 How to use multiple AI models for different tasks (Claude for planning, Gemini for UI) 🔸Specific slash commands to automate key prompts 🔸 Zevi’s “peer review” technique, which uses different LLM models to review each other’s code 🔸 Why this might be the best time to be a junior in tech, despite the challenging job market 🔸 How Zevi used AI to prepare for his Meta PM interviews Listen now 👇 - YouTube: - Spotify: - Apple: Thank you to our wonderful sponsors for supporting the podcast: 🏆 10Web.io — Vibe coding platform as an API 🏆 DX — The developer intelligence platform designed by leading researchers 🏆 Framer — Build better websites faster

The future of product management looks a lot like Zevi Arnovitz Zevi is an IC PM at Meta, has no technical background—is scared to even look at code—but has taught himself how to use Cursor and Claude Code to build significant and real product. He's developed his own very powerful Cursor workflow that allows him to quickly add his ideas to Linear, develop a plan using Claude Code, build it within Cursor, and then have different LLMs review his code. Zevi's engineers at Meta ask him to teach them how he does what he does, and I haven’t stopped thinking about this conversation since we had it. Everyone needs to pay close attention to what AI us unlocking for non-technical people. We discuss: 🔸 The complete AI workflow that lets non-technical people build in Cursor 🔸 How to use multiple AI models for different tasks (Claude for planning, Gemini for UI) 🔸Specific slash commands to automate key prompts 🔸 Zevi’s “peer review” technique, which uses different LLM models to review each other’s code 🔸 Why this might be the best time to be a junior in tech, despite the challenging job market 🔸 How Zevi used AI to prepare for his Meta PM interviews Listen now 👇 - YouTube: - Spotify: - Apple: Thank you to our wonderful sponsors for supporting the podcast: 🏆 10Web.io — Vibe coding platform as an API 🏆 DX — The developer intelligence platform designed by leading researchers 🏆 Framer — Build better websites faster

Lenny Rachitsky

309,688 görüntüleme • 8 ay önce

Introducing Sequenzy - Cursor for your marketing emails 🔥 If you've ever sent emails for your SaaS you know how time-consuming it can be. And if you ask Cursor to do it inside code - you lose analytics, proper segmenting and much much more Sequenzy is an AI-first tool to help you generate on-brand emails and sequences within seconds while STILL having all the benefits of a proper marketing platform You can start for free and get your first email generated in 10 seconds. First sequence - in 1minute(I'm not lying!) Give it a try. Link is in the comment 😙

Nic Polotnianko 🇺🇦

19,524 görüntüleme • 9 ay önce

"Designers will realize—all this back and forth, screenshots, redlines, 50 pixels off—they could just send it to Cursor and it's fixed." As the head of design at Cursor, Ryo Lu is at the cutting edge of designers who ship code instead of mocks. In our new episode, he showed me: ✅ His retro OS (the best vibe app I've seen) ✅ Demo: How he designs & builds with Cursor ✅ How the Cursor team ships products Some quotes from Ryo: "We prototype in Cursor after initial exploration. It lets us interact with real states. It feels a lot more real than static mocks." "Start with one simple app, then keep building. I asked the agent 'what if we make it more retro?' and just kept going from there." "At Cursor, roles between designers, PMs, engineers are muddy. We use our unique strengths and let AI agents tie everything together." Watch now: Also available on: Spotify: Apple: Newsletter:

"Designers will realize—all this back and forth, screenshots, redlines, 50 pixels off—they could just send it to Cursor and it's fixed." As the head of design at Cursor, Ryo Lu is at the cutting edge of designers who ship code instead of mocks. In our new episode, he showed me: ✅ His retro OS (the best vibe app I've seen) ✅ Demo: How he designs & builds with Cursor ✅ How the Cursor team ships products Some quotes from Ryo: "We prototype in Cursor after initial exploration. It lets us interact with real states. It feels a lot more real than static mocks." "Start with one simple app, then keep building. I asked the agent 'what if we make it more retro?' and just kept going from there." "At Cursor, roles between designers, PMs, engineers are muddy. We use our unique strengths and let AI agents tie everything together." Watch now: Also available on: Spotify: Apple: Newsletter:

Peter Yang

108,220 görüntüleme • 10 ay önce

Thank you for the support everyone. Long crazy day. I'm still around this weekend if you want to catch up at Gamescom. I'll be boothless but still in my Mimic shirt (a fresh one DW) so come say hi if you see me :) Looking forward to meeting other Devs and trying out their games.

Thank you for the support everyone. Long crazy day. I'm still around this weekend if you want to catch up at Gamescom. I'll be boothless but still in my Mimic shirt (a fresh one DW) so come say hi if you see me :) Looking forward to meeting other Devs and trying out their games.

Mimic | Ryan Laley

110,065 görüntüleme • 1 ay önce

You can build your own custom Jarvis, using Cursor, Claude Code or Codex, in less than 20 minutes. Using the new GPT-Realtime-2 API... Anything you can do on a computer can be turned into a tool that your Jarvis can use. (Here's exactly how to do it) Introduction Step 1: Cursor Setup Step 2 – Full Jarvis Prompt Step 3 – My Agent Ricky Step 4 – Second Prompt Step 5 – Add EXA API Key for Web Search Step 6 – Third Prompt Step 7 – Add Computer Use Mode Step 8 – Add AI Image Generator (Insane) Final Demo

You can build your own custom Jarvis, using Cursor, Claude Code or Codex, in less than 20 minutes. Using the new GPT-Realtime-2 API... Anything you can do on a computer can be turned into a tool that your Jarvis can use. (Here's exactly how to do it) Introduction Step 1: Cursor Setup Step 2 – Full Jarvis Prompt Step 3 – My Agent Ricky Step 4 – Second Prompt Step 5 – Add EXA API Key for Web Search Step 6 – Third Prompt Step 7 – Add Computer Use Mode Step 8 – Add AI Image Generator (Insane) Final Demo

Riley Brown

62,062 görüntüleme • 3 ay önce

BREAKING NEWS: Anthropic just dropped Claude Ops 4.5!! It is by FAR the best coding model I've ever used. We've been testing it internally Every 📧 for the last few days, and it is an absolute paradigm shift for any kind of coding task. It extends the horizon of what you can vibe code The current generation of new models—Anthropic’s Sonnet 4.5, Google’s Gemini 3, or OpenAI’s Codex Max 5.1—can all competently build a minimum viable product in one shot, or fix a highly technical bug autonomously. But eventually, if you kept pushing them to vibe code more, they’d start to trip over their own feet: The code would be convoluted and contradictory, and you’d get stuck in endless bugs. We have not found that limit yet with Opus 4.5—it seems to be able to vibe code forever. Takes working in parallel to a whole new level because it's far better at planning and coding, it can work with more autonomy—meaning you can do more in parallel without breaking anything . Kieran Klaassen worked on 11 different projects in six hours—and had good results on all of them. Great at design iteration Opus 4.5 is incredibly skilled at iterating through a design autonomously using an MCP like Playwright. previous models would lose the thread after a few cycles, or say a design was done when it wasn't. Opus 4.5 is incredible at autonomously iterating until a design is pixel perfect. we have a full 4,000 word vibe check on Every 📧 right now with everything we tested:

BREAKING NEWS: Anthropic just dropped Claude Ops 4.5!! It is by FAR the best coding model I've ever used. We've been testing it internally Every 📧 for the last few days, and it is an absolute paradigm shift for any kind of coding task. It extends the horizon of what you can vibe code The current generation of new models—Anthropic’s Sonnet 4.5, Google’s Gemini 3, or OpenAI’s Codex Max 5.1—can all competently build a minimum viable product in one shot, or fix a highly technical bug autonomously. But eventually, if you kept pushing them to vibe code more, they’d start to trip over their own feet: The code would be convoluted and contradictory, and you’d get stuck in endless bugs. We have not found that limit yet with Opus 4.5—it seems to be able to vibe code forever. Takes working in parallel to a whole new level because it's far better at planning and coding, it can work with more autonomy—meaning you can do more in parallel without breaking anything . Kieran Klaassen worked on 11 different projects in six hours—and had good results on all of them. Great at design iteration Opus 4.5 is incredibly skilled at iterating through a design autonomously using an MCP like Playwright. previous models would lose the thread after a few cycles, or say a design was done when it wasn't. Opus 4.5 is incredible at autonomously iterating until a design is pixel perfect. we have a full 4,000 word vibe check on Every 📧 right now with everything we tested:

Dan Shipper 📧

272,699 görüntüleme • 10 ay önce

If coding is still your job description, it won't be for long this 9-minute video from the CEO of Cursor is the one talk you can't afford to miss right now 5-10 years ago everyone was saying you should become a programmer, it was the most promising career you could choose. now, without any degree, you can build almost anything if you have the drive and an LLM here's what's already happening: > in 2024, 15% of enterprise code was AI-generated, in 2025 it was 75% > 35% of all PRs at Cursor are now written by agents. no human touches the code > agent usage at Cursor grew 15x in a single year maybe you're reading this and thinking "I already know all of this" and if that's you, there aren't many like you the average Claude user still opens a tab, types something, gets an answer, closes the tab they're using maybe 10% of what Claude can do that's exactly why I built an 18-step guide that helps you set up Claude from scratch and use 100% of its potential even if you've been using Claude for months, there's probably a lot in there that's useful even for you full guide in the article below

If coding is still your job description, it won't be for long this 9-minute video from the CEO of Cursor is the one talk you can't afford to miss right now 5-10 years ago everyone was saying you should become a programmer, it was the most promising career you could choose. now, without any degree, you can build almost anything if you have the drive and an LLM here's what's already happening: > in 2024, 15% of enterprise code was AI-generated, in 2025 it was 75% > 35% of all PRs at Cursor are now written by agents. no human touches the code > agent usage at Cursor grew 15x in a single year maybe you're reading this and thinking "I already know all of this" and if that's you, there aren't many like you the average Claude user still opens a tab, types something, gets an answer, closes the tab they're using maybe 10% of what Claude can do that's exactly why I built an 18-step guide that helps you set up Claude from scratch and use 100% of its potential even if you've been using Claude for months, there's probably a lot in there that's useful even for you full guide in the article below

Anatoli Kopadze

51,491 görüntüleme • 4 ay önce