Video yükleniyor...

Video Yüklenemedi

Ana Sayfaya Dön

Vibe Coding Deathmatch wednesday afternoon full video Bolt, Replit, Cursor, Windsurf head to head building the same project simple prompts across all, the results were: 🥉 Bolt + Windsurf 🥈Cursor 🏆 Replit Reasons: - Bolt was quickest, got into a 'no-audio' issue early and couldnt fix easily. first out,...

59,060 görüntüleme • 1 yıl önce •via X (Twitter)

11 Yorum

Ben Tossell profil fotoğrafı
Ben Tossell1 yıl önce

writeup will be on loom link: and most importantly, the link to play the DJ drums

TurboScribe profil fotoğrafı
TurboScribe1 yıl önce

What REAL customers say about TurboScribe's unlimited AI transcription 👇 🇺🇸 "Not only does it transcribe with amazing accuracy, it also filters out a ton of the unnecessary noise associated with pauses in audio. Keep up the great work!" - Kevin

Faisal Shariff profil fotoğrafı
Faisal Shariff1 yıl önce

It would have been good to see lovable as part of this too! Seems like they mostly all have the same issues. But I agree that I’m also most comfortable with Replit atm. Have you seen alarmingly that Tempolabs have added a ‘hire a dev feature’…what does that say about the confidence in the tech and the future of vibe coding 😥

Ben Tossell profil fotoğrafı
Ben Tossell1 yıl önce

Just a natural add on, people will get stuck and pay to get unstuck. Yeh I’m trying to switch up the tools periodically to see what’s good and not on others

Houman Shadab profil fotoğrafı
Houman Shadab1 yıl önce

Awesome stuff - reminiscent of the No Code Sports League I used to do (most Bubble devs)

Bryan Sanders profil fotoğrafı
Bryan Sanders1 yıl önce

Interesting matchup So who is Superfly Snooka?

Ben Tossell profil fotoğrafı
Ben Tossell1 yıl önce

? No idea

Jason Vu Nguyen profil fotoğrafı
Jason Vu Nguyen1 yıl önce

I agree with your death match results. If you’re not watching cursor carefully, it just goes off the rails.

Sam Jones profil fotoğrafı
Sam Jones1 yıl önce

Nice - this is helpful. Curious to know what transcription software are you using when recording voice instruction at the start?

Ben Tossell profil fotoğrafı
Ben Tossell1 yıl önce

And thanks!

Danny Quiroz profil fotoğrafı
Danny Quiroz1 yıl önce

@amasad Persistent redeploy button 🫡

Benzer Videolar

I've built an AI agent that generates a logline of its choosing, creates text-to-video clips via 'scenes' it prompts with Luma, and then stitches them together automatically—even adding background music if you happen to have some present! At first, I let the model run wild—no direction, just "generate an interesting logline & prompts", basically. The results were quite interesting, but style was a bit all over the place (which was kinda cool in some ways actually). Then, I refined the prompt it was using to create the content—attempting to focus on cinematic feeling, character consistency (age, hair, ethnicity, name), and visual style. The idea is to build it out so that it can (hopefully) stick to genre, director influence, and a cohesive color palette. That will take some time, though. The agent is fully autonomous. It: Writes a story/logline and then the corresponding prompts Generates video clips Downloads them Stitches them into a final video (Optional) Adds background music all in one shot (it just takes ~5-10 minutes, and generates 17 clips or so at this time - I was using 30 as well but shortened it to test). You can upload your own background music to merge seamlessly, too. I'm working on more integrations to refine the output even further. Right now, I want everyone to try it out, but you'll likely need to upload your own API keys (because I'm broke 😂). Still figuring out the best way to share it! I'll have to explore Replit or Gradio, but that will be a little bit either tonight or tomorrow. The final video below shows where it's at as of right now. And in the comments, I’ve included different outputs—some completely chaotic, others more polished after prompt tuning.

Kiri

69,476 görüntüleme • 1 yıl önce

Aman Sanger on scaling Cursor to $100M in revenue in 12 months The four co-founders started working on Cursor in January 2023. “It was about 2-4 months of experimenting, trying different things and finding something that fit,” Aman recalls. “Then we shipped it and it had an okay launch.” The initial version of Cursor got some initial buzz because they shipped it with GPT-4 at a time where very few products were using Open AI’s latest model. But then usage tanked. The team began to doubt their approach after the failed launch. Aman explains: “The entirety of that summer was just incredibly slow growth, and that was somewhat demoralizing. The big question in our minds was, ‘Are we being too ambitious?’ We were trying to build this general purpose thing for all engineers, but with this really small team, maybe we should focus more narrowly on some particular use case like tests or bug detection.” But the fact that they were users of the product gave the team the confidence to keep going down their initial path: “The really magical thing about this product was that we were users of it. So we could iterate incredibly quickly, and we tried all these different things that summer. Then we found this core set of features that worked incredibly well.” The two key features were Command K for instructed edit ability and code-based indexing that let you ask questions about your whole code base. “After we integrated those two features and launched them, growth kind of just took off.” Aman continues: “A lot of the work of Cursor has been just experimenting with what is possible. For everything you see in the product, there’s like 10 failed experiments that didn’t work… All of our work for the first 6 months to a year was trying to find new ways to harness these models and make these models better for programming.” Another factor that contributed to Cursor’s success was their willingness to ship half-finished features: “We released these half-finished things, which a lot of our competitors refused to do. The first version of Copilot++ and Cursor Tab sucked. But once you release it to the world and see how people react to it, you can improve on it a ton… We biased toward releasing as soon as something shows signs of usefulness to the team.” Video source: Peak XV Partners (2025)

Startup Archive

56,166 görüntüleme • 1 yıl önce

I just compared Claude Code vs Codex vs Cursor CLI The task was to build a Next.js app with Tailwind 4 and shadcn components to collect customer feedback and showcase it with a widget. I gave all three the same prompt and let them go for 30 minutes to see what they came up with. Claude Code with Opus 4.1 Even though I told it to set up the app in the existing project folder, it tried to create a directory for it. After I interrupted and told it not to do that, it built a demo form and landing page with no errors. I had to ask it to make the demo interactive so users could submit a testimonial and preview it. The landing page looked like AI and was pretty basic, but it worked and it was done in a fraction of the time of the others. Total tokens used: 33k Codex with GPT-5 At the end of the 30 minutes I just could not get Codex to produce a working app. It got stuck in a loop of not being able to set up Tailwind 4 and despite many, MANY, attempts, I ended up with a "failed to compile" error. Total tokens used: 102k Cursor Agent with GPT-5 This was the slowest agent by far and a couple of times I actually thought it got stuck in a loop and was close to Ctrl+C'ing to cancel it. The TUI is really nice though, especially how it shows diffs and it did eventually build a working app (after one or two slight errors that needed fixing) The demo was interactive and it had a very minimal design that looked bare but also a lot less like an "AI generated" app than the Opus 4.1 design. It also wasn't too chatty and just did what it needed to do! Code quality was on a par with Opus 4.1, but it did use 5.5x as many tokens to get there. Still cheaper than Opus on a direct comparison but not when you factor in a Claude Code Max subscription. Total tokens: 188k I'll be able to do a proper comparison and record some videos when I'm back from holiday but for now, Opus is still the more capable model out of the box and Claude Code is the more complete CLI product. It will be interesting to see how Cursor evolve their CLI though with commands and subagents because I think with GPT-5 they have a real shot at providing competition for Claude Code if they can optimise output to get similar quality with less tokens. Jump to 0:40 in the video to see the two apps. Which do you think is which? ;)

Ian Nuttall

194,949 görüntüleme • 11 ay önce