Video wird geladen...

Video konnte nicht geladen werden

Zur Startseite

Better Cursor alternative? I've been playing with the new AI IDE Windsurf launched by Codeium past few days, and the result was impressive, particularly: 1. Code base understanding: One thing Windsurf did really well is its understanding of the whole code base & dependencies; This led to a big...

jasonzhou1993's profile picture

Jason Zhou

29,101 subscribers

64,713 Aufrufe • vor 1 Jahr •via X (Twitter)

Wissenschaft & TechnologieComedy
LIVE

Anya Rossi• Live Now

Private livecam show

10 Kommentare

Profilbild von Julian Harris
Julian Harrisvor 1 Jahr

@codeiumdev If I’m working with APIs or libraries that are new or changed in the last 12 months (hint: almost everything) the only way code-gen works reliably for me is if there’s a web search in the loop. I’ve struggled to get Cursor to do this reliably. What about Windsurf?

Profilbild von Jason Zhou
Jason Zhouvor 1 Jahr

@codeiumdev Ideally yes.. I just paste doc in, and I found windsurf follows better than cursor in my experience; But still, it tends to revert back to old knowledge unless you prompt it hard

Profilbild von Edwardooo
Edwardooovor 1 Jahr

@codeiumdev I have been using cursor for three months daily. I just tried Windsurf. I say it is pretty smart. It learned the code base to make a new page that plot all the locations. (with auto zoomout to see all the spots )

Profilbild von Phatic
Phaticvor 1 Jahr

@codeiumdev Welp

Profilbild von Jason Zhou
Jason Zhouvor 1 Jahr

@codeiumdev Oh woah, didn’t know about this, pretty exciting

Profilbild von Louiepecan.base.eth🗡🛡
Louiepecan.base.eth🗡🛡vor 1 Jahr

@codeiumdev @grandorganics

Profilbild von George Siosi Samuels
George Siosi Samuelsvor 1 Jahr

@codeiumdev Just downloaded

Profilbild von Axel Sachmann
Axel Sachmannvor 1 Jahr

@codeiumdev Thx for the great presentation 🙏

Profilbild von konstantinpaulus
konstantinpaulusvor 1 Jahr

@codeiumdev

Profilbild von pharo
pharovor 1 Jahr

@codeiumdev I tried it today Feels more powerful than cursor But I have to test it more

Ähnliche Videos

Is Windsurf better than Cursor? impossible to say, but... it does one thing better: soooo... I spent an hour testing windsurf... and this is what i created... and app called "boop-boop" lol... one thing windsurf does is it searches the internet. If you've been watching my videos you know that i go to perplexity all the time to get code examples and docs. but with windsurf you can just say, "search the replicate top image gen models and add them to the chat we just created" It will search the internet, find the right model then write the code. This is great for replicate and openrouter. You can have one api key in your .env file then just tell windsurf to search for docs for [insert ai model] and it will just add it to your app. Impressed tbh.
2:30

Is Windsurf better than Cursor? impossible to say, but... it does one thing better: soooo... I spent an hour testing windsurf... and this is what i created... and app called "boop-boop" lol... one thing windsurf does is it searches the internet. If you've been watching my videos you know that i go to perplexity all the time to get code examples and docs. but with windsurf you can just say, "search the replicate top image gen models and add them to the chat we just created" It will search the internet, find the right model then write the code. This is great for replicate and openrouter. You can have one api key in your .env file then just tell windsurf to search for docs for [insert ai model] and it will just add it to your app. Impressed tbh.

Riley Brown

31,043 Aufrufe • vor 1 Jahr

Have you ever vibe coded 6 versions of same app at the same time using all of the best AI coding tools. Well I did it in this video: Tools used: Cursor Cursor Windsurf @windsurf Replit Replit ⠕ Bolt bolt.new Lovable v0 TimeStamps 00:00 - Introduction to AI Coding Tools 01:23 - First Prompts 05:56 - Final Adjustments and Comparisons 16:12 - Results / Rankings don't worry a cancelled my api keys
17:49

Have you ever vibe coded 6 versions of same app at the same time using all of the best AI coding tools. Well I did it in this video: Tools used: Cursor Cursor Windsurf @windsurf Replit Replit ⠕ Bolt bolt.new Lovable v0 TimeStamps 00:00 - Introduction to AI Coding Tools 01:23 - First Prompts 05:56 - Final Adjustments and Comparisons 16:12 - Results / Rankings don't worry a cancelled my api keys

Riley Brown

173,916 Aufrufe • vor 1 Jahr

I've been playing with MiniMax M3 recently. The combination of coding, agent workflows, 1M context, and multimodal understanding made me curious enough to try something real. So I gave it one task: "Build me a Skill Hub to manage all my Claude Code skills."👇
0:46

I've been playing with MiniMax M3 recently. The combination of coding, agent workflows, 1M context, and multimodal understanding made me curious enough to try something real. So I gave it one task: "Build me a Skill Hub to manage all my Claude Code skills."👇

ares. 🎧

49,239 Aufrufe • vor 1 Monat

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.
5:21

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

63,262 Aufrufe • vor 1 Jahr

Will tools like Windsurf result in fewer software engineers? "It feels like it's people hating software engineers who say this" says Windsurf cofounder and CEO Varun Mohan In today's podcast episode, we go into the engineering challenges (and tradeoffs!) of building an AI-powered IDE like Windsurf and how Windsurf has changed how the Windsurf dev team (and non-developers!) write software. Watch or listen: • YouTube: • Spotify: • Apple: Brought to you by: • CodeRabbit — Cut code review time and bugs in half. Use the code PRAGMATIC to get one month free at • Modal — The cloud platform for building AI applications Get started at Three of my takeaways: 𝟭. 𝗔𝗜-𝗽𝗼𝘄𝗲𝗿𝗲𝗱 𝗜𝗗𝗘𝘀 𝗺𝗮𝗸𝗲 𝗲𝗻𝗴𝗶𝗻𝗲𝗲𝗿𝘀 𝗺𝗼𝗿𝗲 “𝗳𝗲𝗮𝗿𝗹𝗲𝘀𝘀” 𝗮𝗻𝗱 𝗰𝗼𝘂𝗹𝗱 𝗿𝗲𝗱𝘂𝗰𝗲 𝗺𝗲𝗻𝘁𝗮𝗹 𝗹𝗼𝗮𝗱. I asked Varun how using Windsurf changed the workload and output of engineers — especially given how most of the team have been software engineers well before LLM coding assistants were a thing. A few of Varun’s observations: • Engineers are more “fearless” in jumping into unfamiliar parts of the codebase — when, in the past, they would have waited to talk to people more familar with the code. • Devs increasingly first turn to AI for help, before pinging someone else (and thus interrupting that person) • Mental fatigue is down, thanks to tedious tasks can be handed off to prompts or AI agents Varun stressed that he doesn’t see tools like Windsurf eliminating the need for skilled engineers: it simply changes the nature of the work, and can increase potential output. 𝟮. 𝗙𝗼𝗿𝗸𝗶𝗻𝗴 𝗩𝗦 𝗖𝗼𝗱𝗲 𝘁𝗵𝗲 “𝗿𝗶𝗴𝗵𝘁” 𝘄𝗮𝘆 𝗺𝗲𝗮𝗻𝘀 𝗱𝗼𝗶𝗻𝗴 𝗮 𝗹𝗼𝘁 𝗼𝗳 𝗶𝗻𝘃𝗶𝘀𝗶𝗯𝗹𝗲 𝘄𝗼𝗿𝗸. While VS Code is open source and can be forked: VS Code Marketplace and lots of proprietary extensions. For example, when forking VS Code, the fork is not allowed to use extensions like Python language servers, remote SSH, and dev containers. The Windsurf team had to build custom extensions from scratch — which took a bunch of time, and users probably did not even notice the difference! However, if Windsurf had not done this, and had broken the license of these extensions, they could have found themselves in legal hot water. So forking VS Code “properly” is not as simple as most devs would normally expect. 𝟯. 𝗖𝗼𝘂𝗹𝗱 𝘄𝗲 𝘀𝗲𝗲 𝗺𝗼𝗿𝗲 𝗻𝗼𝗻-𝗱𝗲𝘃𝗲𝗹𝗼𝗽𝗲𝗿𝘀 𝗰𝗿𝗲𝗮𝘁𝗲 “𝘄𝗼𝗿𝗸 𝘀𝗼𝗳𝘁𝘄𝗮𝗿𝗲?” 𝗠𝗮𝘆𝗯𝗲. One of the very surprising stories was how Windsurf’s partnership lead (a non-developer) created a quoting tool by prompting Windsurf. This tool replaced a bespoke, stateless tool that the company paid for. Varun and I agreed that a complex SaaS that has lots of state and other features is not really a target to be “replaced internally.” However, simple pieces of software can now be “prompted” by business users. I have my doubts about how maintainable these will be in the long run: just thinking about how even Big Tech struggles with internal tools built by a single dev, and then when this dev leaves, no one wants to take it over.
0:36

Will tools like Windsurf result in fewer software engineers? "It feels like it's people hating software engineers who say this" says Windsurf cofounder and CEO Varun Mohan In today's podcast episode, we go into the engineering challenges (and tradeoffs!) of building an AI-powered IDE like Windsurf and how Windsurf has changed how the Windsurf dev team (and non-developers!) write software. Watch or listen: • YouTube: • Spotify: • Apple: Brought to you by: • CodeRabbit — Cut code review time and bugs in half. Use the code PRAGMATIC to get one month free at • Modal — The cloud platform for building AI applications Get started at Three of my takeaways: 𝟭. 𝗔𝗜-𝗽𝗼𝘄𝗲𝗿𝗲𝗱 𝗜𝗗𝗘𝘀 𝗺𝗮𝗸𝗲 𝗲𝗻𝗴𝗶𝗻𝗲𝗲𝗿𝘀 𝗺𝗼𝗿𝗲 “𝗳𝗲𝗮𝗿𝗹𝗲𝘀𝘀” 𝗮𝗻𝗱 𝗰𝗼𝘂𝗹𝗱 𝗿𝗲𝗱𝘂𝗰𝗲 𝗺𝗲𝗻𝘁𝗮𝗹 𝗹𝗼𝗮𝗱. I asked Varun how using Windsurf changed the workload and output of engineers — especially given how most of the team have been software engineers well before LLM coding assistants were a thing. A few of Varun’s observations: • Engineers are more “fearless” in jumping into unfamiliar parts of the codebase — when, in the past, they would have waited to talk to people more familar with the code. • Devs increasingly first turn to AI for help, before pinging someone else (and thus interrupting that person) • Mental fatigue is down, thanks to tedious tasks can be handed off to prompts or AI agents Varun stressed that he doesn’t see tools like Windsurf eliminating the need for skilled engineers: it simply changes the nature of the work, and can increase potential output. 𝟮. 𝗙𝗼𝗿𝗸𝗶𝗻𝗴 𝗩𝗦 𝗖𝗼𝗱𝗲 𝘁𝗵𝗲 “𝗿𝗶𝗴𝗵𝘁” 𝘄𝗮𝘆 𝗺𝗲𝗮𝗻𝘀 𝗱𝗼𝗶𝗻𝗴 𝗮 𝗹𝗼𝘁 𝗼𝗳 𝗶𝗻𝘃𝗶𝘀𝗶𝗯𝗹𝗲 𝘄𝗼𝗿𝗸. While VS Code is open source and can be forked: VS Code Marketplace and lots of proprietary extensions. For example, when forking VS Code, the fork is not allowed to use extensions like Python language servers, remote SSH, and dev containers. The Windsurf team had to build custom extensions from scratch — which took a bunch of time, and users probably did not even notice the difference! However, if Windsurf had not done this, and had broken the license of these extensions, they could have found themselves in legal hot water. So forking VS Code “properly” is not as simple as most devs would normally expect. 𝟯. 𝗖𝗼𝘂𝗹𝗱 𝘄𝗲 𝘀𝗲𝗲 𝗺𝗼𝗿𝗲 𝗻𝗼𝗻-𝗱𝗲𝘃𝗲𝗹𝗼𝗽𝗲𝗿𝘀 𝗰𝗿𝗲𝗮𝘁𝗲 “𝘄𝗼𝗿𝗸 𝘀𝗼𝗳𝘁𝘄𝗮𝗿𝗲?” 𝗠𝗮𝘆𝗯𝗲. One of the very surprising stories was how Windsurf’s partnership lead (a non-developer) created a quoting tool by prompting Windsurf. This tool replaced a bespoke, stateless tool that the company paid for. Varun and I agreed that a complex SaaS that has lots of state and other features is not really a target to be “replaced internally.” However, simple pieces of software can now be “prompted” by business users. I have my doubts about how maintainable these will be in the long run: just thinking about how even Big Tech struggles with internal tools built by a single dev, and then when this dev leaves, no one wants to take it over.

Gergely Orosz

34,355 Aufrufe • vor 1 Jahr

I tested a new coding assistant on 34,568 lines of code. (Cursor could not achieve what this tool did.) AI models are improving every day: - Faster inference - Longer context lengths But are AI coding assistants advancing at the same rate? Can they truly understand your entire project? I tested Augment Code on my ai-engineering repo with ~35k lines of code. Augment Code is a powerful AI Assistant built for developers working with large, evolving codebases—needing an assistant that understands the full context of their projects. In the video demo below, I asked it to: - Merge two projects. - Answer a global context question. Here’s what happened: - It understood dependencies across both projects. - It merged them intelligently—without breaking anything. - It even created a README file for the merged project. - It answered my global query instantly, pulling from the full codebase. This is the difference between AI autocomplete and an AI engineer that truly understands your repo. Augment Code is powerful because it indexes your entire repo upfront. This way, it can answer questions instantly, no matter how large your project is. Lastly, Augment Code is fully compatible with VSCode, JetBrains, Vim, Slack, and more. Try them now, I have shared a link in the next tweet! Thanks to Augment Code for showing me their powerful AI coding assistant and working with me on this post.
0:31

I tested a new coding assistant on 34,568 lines of code. (Cursor could not achieve what this tool did.) AI models are improving every day: - Faster inference - Longer context lengths But are AI coding assistants advancing at the same rate? Can they truly understand your entire project? I tested Augment Code on my ai-engineering repo with ~35k lines of code. Augment Code is a powerful AI Assistant built for developers working with large, evolving codebases—needing an assistant that understands the full context of their projects. In the video demo below, I asked it to: - Merge two projects. - Answer a global context question. Here’s what happened: - It understood dependencies across both projects. - It merged them intelligently—without breaking anything. - It even created a README file for the merged project. - It answered my global query instantly, pulling from the full codebase. This is the difference between AI autocomplete and an AI engineer that truly understands your repo. Augment Code is powerful because it indexes your entire repo upfront. This way, it can answer questions instantly, no matter how large your project is. Lastly, Augment Code is fully compatible with VSCode, JetBrains, Vim, Slack, and more. Try them now, I have shared a link in the next tweet! Thanks to Augment Code for showing me their powerful AI coding assistant and working with me on this post.

Akshay 🚀

30,806 Aufrufe • vor 1 Jahr

Reviewing AI-generated code is the new bottleneck. Writing code was slow before. Now, in a few minutes, you can generate virtually unlimited lines of code using AI. But developers are now spending 70% of their time checking that code. That's the new bottleneck. I've been using Cline, and they have a feature that actually helps with this: You can click a button and have Cline generate an inline explanation for every single line of AI-generated code. Take a look at the attached video. What it does: 1. You can read the code and the explanation together 2. You don't lose context while reviewing code 3. You understand the "why" behind each change And here is the best part: It works on any git diff. You can use it to review PRs, understand commits from other people, or catch up on a codebase you haven't touched in a while.
3:25

Reviewing AI-generated code is the new bottleneck. Writing code was slow before. Now, in a few minutes, you can generate virtually unlimited lines of code using AI. But developers are now spending 70% of their time checking that code. That's the new bottleneck. I've been using Cline, and they have a feature that actually helps with this: You can click a button and have Cline generate an inline explanation for every single line of AI-generated code. Take a look at the attached video. What it does: 1. You can read the code and the explanation together 2. You don't lose context while reviewing code 3. You understand the "why" behind each change And here is the best part: It works on any git diff. You can use it to review PRs, understand commits from other people, or catch up on a codebase you haven't touched in a while.

Santiago

64,399 Aufrufe • vor 7 Monaten

Forget Roo, Cline, Windsurf, Cursor. Augment Code keeps raising the bar. Tried it on a fun project I hadn’t touched in months. Instead of random refactors, it rebuilt the architecture coherently, understanding the whole codebase → structure, dependencies + Git history. And where tools like Cursor often struggle with large repos or lose track of cross-file relationships... Augment mapped everything. Instantly 🤯 Once the full context is loaded, you can move ridiculously fast: → Restructure / rename components across repos → Swap between GPT-5, Claude Sonnet 4 / 4.5, and Claude Haiku via their Model Picker → Offload builds, tests, deploys to Remote Agents A few extras I really loved: → I could stay in VS Code, JetBrains IDEs... even Vim, which is v. cool! → If you prefer the terminal, the Auggie CLI now gives you the same experience headless. → It also handled a bunch of massive repos I threw at it smoothly, while Cursor struggled to even index them! → It always previews planned refactors before running them 🫶 ____ You can give Augment Code a try here → Big thx to the Augment Code team for partnering with me on this post, I learned a ton along the way! 🙏
0:31

Forget Roo, Cline, Windsurf, Cursor. Augment Code keeps raising the bar. Tried it on a fun project I hadn’t touched in months. Instead of random refactors, it rebuilt the architecture coherently, understanding the whole codebase → structure, dependencies + Git history. And where tools like Cursor often struggle with large repos or lose track of cross-file relationships... Augment mapped everything. Instantly 🤯 Once the full context is loaded, you can move ridiculously fast: → Restructure / rename components across repos → Swap between GPT-5, Claude Sonnet 4 / 4.5, and Claude Haiku via their Model Picker → Offload builds, tests, deploys to Remote Agents A few extras I really loved: → I could stay in VS Code, JetBrains IDEs... even Vim, which is v. cool! → If you prefer the terminal, the Auggie CLI now gives you the same experience headless. → It also handled a bunch of massive repos I threw at it smoothly, while Cursor struggled to even index them! → It always previews planned refactors before running them 🫶 ____ You can give Augment Code a try here → Big thx to the Augment Code team for partnering with me on this post, I learned a ton along the way! 🙏

Charly Wargnier

31,025 Aufrufe • vor 8 Monaten

Using the 6 best Vibe Coding Tools AT THE SAME TIME Without writing a single line of code @lovable_dev - Landing Page bolt.new - Writing App w/ AI chat Replit ⠕ - To-Do List App Cursor - AI Image Tool (figma + ai gen) @windsurf - Perplexity v0 - Portfolio I didn't have a plan beyond this. I just wanted to know what it felt like to vibe code using 6 tools at once. This is simply an exploration. (This is not a tutorial lol) ------------------------------- 00:00 Intro / Plan 00:46 First Prompt for 6 apps 03:20 Most of "Coding" was already copy and paste 10:48 Start Round 2 (Prompt 2) 15:41 Round 3 Prompting 27:42 "The chicken that i generated" 28:30 "Its fine we're creating 6 projects at once" 29:43 "Gotta Leave one Booyah in There" 33:55 "You Know what Lovable, Respect, it looks horrid, but you're on the right track" 35:51 "Bolt, Don't exactly listen to me, but like, mostly listen to me" 39:12 "v0 we're in it, you know it's not horrible, it's bad" 40:47 Bolt, you dawg!!! well done 43:39 Windsurf Web Search is Working! 50:29 Downloading v0 as zip and putting into cursor 55:14 What I made in this session
59:21

Using the 6 best Vibe Coding Tools AT THE SAME TIME Without writing a single line of code @lovable_dev - Landing Page bolt.new - Writing App w/ AI chat Replit ⠕ - To-Do List App Cursor - AI Image Tool (figma + ai gen) @windsurf - Perplexity v0 - Portfolio I didn't have a plan beyond this. I just wanted to know what it felt like to vibe code using 6 tools at once. This is simply an exploration. (This is not a tutorial lol) ------------------------------- 00:00 Intro / Plan 00:46 First Prompt for 6 apps 03:20 Most of "Coding" was already copy and paste 10:48 Start Round 2 (Prompt 2) 15:41 Round 3 Prompting 27:42 "The chicken that i generated" 28:30 "Its fine we're creating 6 projects at once" 29:43 "Gotta Leave one Booyah in There" 33:55 "You Know what Lovable, Respect, it looks horrid, but you're on the right track" 35:51 "Bolt, Don't exactly listen to me, but like, mostly listen to me" 39:12 "v0 we're in it, you know it's not horrible, it's bad" 40:47 Bolt, you dawg!!! well done 43:39 Windsurf Web Search is Working! 50:29 Downloading v0 as zip and putting into cursor 55:14 What I made in this session

Riley Brown

79,821 Aufrufe • vor 1 Jahr

I've been using Playwright MCP in my coding workflow for 2 use cases: 1. Cursor Self-iterate UI 2. AI-driven test automation With the recent image support, it is getting even better. ------ Here is how I do it: 0:00 Playwright intro 2:43 My Setup 6:00 Use case 1: Iterate UI 7:20 Use case 2: Automated testing If you want to learn AI coding beyond basics, Join AI Builder Club where I post tips weekly:
10:30

I've been using Playwright MCP in my coding workflow for 2 use cases: 1. Cursor Self-iterate UI 2. AI-driven test automation With the recent image support, it is getting even better. ------ Here is how I do it: 0:00 Playwright intro 2:43 My Setup 6:00 Use case 1: Iterate UI 7:20 Use case 2: Automated testing If you want to learn AI coding beyond basics, Join AI Builder Club where I post tips weekly:

Jason Zhou

21,886 Aufrufe • vor 1 Jahr

Klarna CEO Sebastian Siemiatkowski never learned how to code. But after a summer using Cursor, he now brings working prototypes to meetings instead of asking engineers to interpret his ideas: “Because I'm not an engineer, I've been vibe coding my whole life.” “I come into the meeting room, there's tons of product people and engineers. I say, ‘I think we should build an app that kind of does this, and it should work like that.’ They try to make sense of what is saying.” “I've never seen the code. I don't know how they made it. It's beautiful, I like our app. I think it's nice but, I don't know how it works.” “So to me, I've been vibe coding for 20 years. The only difference is now I'm sitting with a computer, and I'm doing it with AI and it's coming back with the prototype in 20 minutes.”
3:02

Klarna CEO Sebastian Siemiatkowski never learned how to code. But after a summer using Cursor, he now brings working prototypes to meetings instead of asking engineers to interpret his ideas: “Because I'm not an engineer, I've been vibe coding my whole life.” “I come into the meeting room, there's tons of product people and engineers. I say, ‘I think we should build an app that kind of does this, and it should work like that.’ They try to make sense of what is saying.” “I've never seen the code. I don't know how they made it. It's beautiful, I like our app. I think it's nice but, I don't know how it works.” “So to me, I've been vibe coding for 20 years. The only difference is now I'm sitting with a computer, and I'm doing it with AI and it's coming back with the prototype in 20 minutes.”

sourcery

149,352 Aufrufe • vor 6 Monaten

Notion's Head of Product Max Schoening : "I actually don't care at all whether designers write code that lands in production. The reason I like designers thinking in code is that it forces you to consider the medium. I would much rather take a designer or PM who has a deep affinity for understanding how agent loops work than someone who can ship PRs. And the only way that you can actually get to understanding agent loops is by building them in the material that they're made of, which is currently code. That's why I care that designers 'code.' Not because of the utility of shipping to production, but because it forces you to really interrogate the material that you're designing with."
0:56

Notion's Head of Product Max Schoening : "I actually don't care at all whether designers write code that lands in production. The reason I like designers thinking in code is that it forces you to consider the medium. I would much rather take a designer or PM who has a deep affinity for understanding how agent loops work than someone who can ship PRs. And the only way that you can actually get to understanding agent loops is by building them in the material that they're made of, which is currently code. That's why I care that designers 'code.' Not because of the utility of shipping to production, but because it forces you to really interrogate the material that you're designing with."

Lenny Rachitsky

76,242 Aufrufe • vor 2 Monaten

I built an agent that answers machine-learning questions. It's autonomous, and the best part is that I built the whole thing without writing a single line of Python code. Here is what I did and how I did it: Over a year ago, a friend and I built a site that publishes multi-choice questions. You get a new one every day. I decided to have GPT-3.5 answer questions. Here is what I needed to build: 1. Connect to the site's API to retrieve today's question 2. Extract the question and the potential choices 3. Connect to OpenAI's API and ask GPT-3.5 to answer the question 4. Parse the answer from the model 5. Submit the answer back to the API to get the score Not difficult. Likely several hours of work. But I didn't have to write any code. I built the whole thing by dragging and dropping components using Vellum is a YC-backed platform for developers to build LLM applications. They are the only ones I've seen offering this functionality. They sponsored this post, and their team helped me with all my questions while I built this. I created a workflow. The platform supports several node types to build whatever you have in mind. I show how I put the whole thing together in the attached video. The only code I had to write was a few lines of Jinja to parse and transform the API and the LLM results. There are three lessons I want to share from this experience: First, the best possible code is the one you didn't write. I'm a big fan of no-code tools because they help me materialize my ideas fast. They help product people, designers, and no coders collaborate on the solution. Second, Large Language Models are sensitive to how you prompt them. Small changes to prompts can make a big difference in results. This is more pronounced when you are building a multi-step workflow. Third, automated testing and evaluation for prompts is critical. There aren't many companies thinking about this. They'll have a hard time moving from a demo phase. The attached video will show you what I did.
3:46

I built an agent that answers machine-learning questions. It's autonomous, and the best part is that I built the whole thing without writing a single line of Python code. Here is what I did and how I did it: Over a year ago, a friend and I built a site that publishes multi-choice questions. You get a new one every day. I decided to have GPT-3.5 answer questions. Here is what I needed to build: 1. Connect to the site's API to retrieve today's question 2. Extract the question and the potential choices 3. Connect to OpenAI's API and ask GPT-3.5 to answer the question 4. Parse the answer from the model 5. Submit the answer back to the API to get the score Not difficult. Likely several hours of work. But I didn't have to write any code. I built the whole thing by dragging and dropping components using Vellum is a YC-backed platform for developers to build LLM applications. They are the only ones I've seen offering this functionality. They sponsored this post, and their team helped me with all my questions while I built this. I created a workflow. The platform supports several node types to build whatever you have in mind. I show how I put the whole thing together in the attached video. The only code I had to write was a few lines of Jinja to parse and transform the API and the LLM results. There are three lessons I want to share from this experience: First, the best possible code is the one you didn't write. I'm a big fan of no-code tools because they help me materialize my ideas fast. They help product people, designers, and no coders collaborate on the solution. Second, Large Language Models are sensitive to how you prompt them. Small changes to prompts can make a big difference in results. This is more pronounced when you are building a multi-step workflow. Third, automated testing and evaluation for prompts is critical. There aren't many companies thinking about this. They'll have a hard time moving from a demo phase. The attached video will show you what I did.

Santiago

309,825 Aufrufe • vor 2 Jahren

AI STARTUPS ARE WRITING CODE FASTER THAN HUMANS AND RAISING BILLIONS WHILE THEY’RE AT IT AI now writes code for apps, games, and websites faster and cheaper than people. Cursor raised $900 million at a $10 billion valuation. Windsurf may sell to OpenAI for $3 billion. Their tools turn plain English into working code. Google says over 30 percent of its code is AI-written. Amazon saved 4,500 developer-years. Microsoft said 30 percent of its code is AI-made and laid off 6,000 workers. Despite high revenue, these startups are losing money. Cursor makes $100 million but spends more. Windsurf earns $50 million and is also in the red due to steep AI model costs. To cut expenses, Poolside raised $600 million to build its own AI. Magic Dev raised $500 million but has yet to launch a product. Everyone is racing to dominate before Big Tech does. Entry-level coding jobs are disappearing. The machines are not coming. They are already here. Source: Reuters
1:36

AI STARTUPS ARE WRITING CODE FASTER THAN HUMANS AND RAISING BILLIONS WHILE THEY’RE AT IT AI now writes code for apps, games, and websites faster and cheaper than people. Cursor raised $900 million at a $10 billion valuation. Windsurf may sell to OpenAI for $3 billion. Their tools turn plain English into working code. Google says over 30 percent of its code is AI-written. Amazon saved 4,500 developer-years. Microsoft said 30 percent of its code is AI-made and laid off 6,000 workers. Despite high revenue, these startups are losing money. Cursor makes $100 million but spends more. Windsurf earns $50 million and is also in the red due to steep AI model costs. To cut expenses, Poolside raised $600 million to build its own AI. Magic Dev raised $500 million but has yet to launch a product. Everyone is racing to dominate before Big Tech does. Entry-level coding jobs are disappearing. The machines are not coming. They are already here. Source: Reuters

Mario Nawfal

118,552 Aufrufe • vor 1 Jahr

This is one of the coolest open-source AI agent projects I've seen in a while: 'Understand Anything' It's a plugin for Claude Code, Codex, OpenCode etc. that analyzes your codebase and turns it into a knowledge base that you can interact with. It explains the codebase to you, rather than showing you the structure. It seems like it's designed for code but I opened my Obsidian vault of podcast highlights in Claude Code, then ran /understand. The result is a knowledge graph that I can search of highlights from 888 podcast episodes and 144K lines of markdown text.
0:22

This is one of the coolest open-source AI agent projects I've seen in a while: 'Understand Anything' It's a plugin for Claude Code, Codex, OpenCode etc. that analyzes your codebase and turns it into a knowledge base that you can interact with. It explains the codebase to you, rather than showing you the structure. It seems like it's designed for code but I opened my Obsidian vault of podcast highlights in Claude Code, then ran /understand. The result is a knowledge graph that I can search of highlights from 888 podcast episodes and 144K lines of markdown text.

Dan McAteer

173,339 Aufrufe • vor 1 Monat