Loading video...

Video Failed to Load

Go Home

As no-code design tools become more common, so do the pitfalls. You know what they look like - the purple gradients, annoying hover effects, sections that fade as you scroll. So how do you avoid a site that feels vibe coded while still taking advantage of these new tools?...

ycombinator's profile picture

Y Combinator

1,619,859 subscribers

84,834 views • 8 months ago •via X (Twitter)

Science & TechnologyEducation
LIVE

Anya Rossi• Live Now

Private livecam show

0 Comments

No comments available

Comments from the original post will appear here

Related Videos

AI is dramatically changing the way we interact with software. For Design Review, YC's Aaron Epstein is joined by Raphael Schaad, founder & designer of Cron (now Notion Calendar), to look at examples of new AI interfaces, from agents and adaptive UI to video prompts and voice.
1:21

AI is dramatically changing the way we interact with software. For Design Review, YC's Aaron Epstein is joined by Raphael Schaad, founder & designer of Cron (now Notion Calendar), to look at examples of new AI interfaces, from agents and adaptive UI to video prompts and voice.

Y Combinator

71,052 views • 1 year ago

AI isn't just changing the tools designers use. It's changing how they build, ship, and stand out. In this episode of Design Review, Stephen Haney, founder of AI-native design tool Paper, joins YC's Aaron Epstein to demo the agent-first workflow that's making Paper one of the fastest-growing design tools since Figma. Using live redesigns of user-submitted websites as examples, they break down the most common AI design tells, show how to fix them in seconds, and explain why the biggest risk for founders isn't moving too slow, it's shipping something that looks like everyone else. 01:04 - What is Paper and why build it? 03:17 - What makes Paper agent-native 05:11 - Demo: Shaders, image generation, and brand design 11:32 - Design-to-code and the new agent stack 16:48 - Design Review: Legion Health 24:11 - How to avoid AI design slop 28:26 - Design Review: Sytex 32:42 - The biggest tells of AI-generated design 37:39 - Design Review: Moreta 41:11 - Can AI learn taste? 43:56 - How Paper uses agents internally 46:52 - Building a community around Paper 49:15 - Lessons from Steven’s first startup 53:30 - What’s next for design and Paper
56:01

AI isn't just changing the tools designers use. It's changing how they build, ship, and stand out. In this episode of Design Review, Stephen Haney, founder of AI-native design tool Paper, joins YC's Aaron Epstein to demo the agent-first workflow that's making Paper one of the fastest-growing design tools since Figma. Using live redesigns of user-submitted websites as examples, they break down the most common AI design tells, show how to fix them in seconds, and explain why the biggest risk for founders isn't moving too slow, it's shipping something that looks like everyone else. 01:04 - What is Paper and why build it? 03:17 - What makes Paper agent-native 05:11 - Demo: Shaders, image generation, and brand design 11:32 - Design-to-code and the new agent stack 16:48 - Design Review: Legion Health 24:11 - How to avoid AI design slop 28:26 - Design Review: Sytex 32:42 - The biggest tells of AI-generated design 37:39 - Design Review: Moreta 41:11 - Can AI learn taste? 43:56 - How Paper uses agents internally 46:52 - Building a community around Paper 49:15 - Lessons from Steven’s first startup 53:30 - What’s next for design and Paper

Y Combinator

119,049 views • 3 months ago

In this episode of Design Review, YC’s Aaron Epstein sat down with Framer CEO and co-founder, Jorn van Dijk, to review user-submitted websites built using Framer. They'll share practical advice on how to clearly communicate what your product does, when animation helps (and when it hurts), and how to use Framer’s powerful tools without ending up with a site that feels generic or overly templatized. 00:00 - Intro 00:30 - Lumari 07:20 - Alai 15:00 - Juicebox 24:00 - LeapingAI 30:10 - The Hog
40:26

In this episode of Design Review, YC’s Aaron Epstein sat down with Framer CEO and co-founder, Jorn van Dijk, to review user-submitted websites built using Framer. They'll share practical advice on how to clearly communicate what your product does, when animation helps (and when it hurts), and how to use Framer’s powerful tools without ending up with a site that feels generic or overly templatized. 00:00 - Intro 00:30 - Lumari 07:20 - Alai 15:00 - Juicebox 24:00 - LeapingAI 30:10 - The Hog

Y Combinator

34,693 views • 9 months ago

In this special episode of Design Review, YC General Partner Aaron Epstein and YC Product Designer eve break down how they went about redesigning the YC homepage from the ground up. They’ll discuss the motivations for the redesign, the unconventional process they took and lessons for founders building their own sites. 00:00 — Designing A New Website 01:00 — The Old Homepage 02:30 — Centering the Story on Founders 04:00 — The New Vision: Inspire, Don’t Sell 05:30 — Visualizing Founder Transformation 07:00 — Letting Founders Speak for Themselves 08:45 — Bringing YC’s Network to Life 12:00 — Minimal Design 17:00 — The Future of Interactive Web Design
18:39

In this special episode of Design Review, YC General Partner Aaron Epstein and YC Product Designer eve break down how they went about redesigning the YC homepage from the ground up. They’ll discuss the motivations for the redesign, the unconventional process they took and lessons for founders building their own sites. 00:00 — Designing A New Website 01:00 — The Old Homepage 02:30 — Centering the Story on Founders 04:00 — The New Vision: Inspire, Don’t Sell 05:30 — Visualizing Founder Transformation 07:00 — Letting Founders Speak for Themselves 08:45 — Bringing YC’s Network to Life 12:00 — Minimal Design 17:00 — The Future of Interactive Web Design

Y Combinator

25,247 views • 9 months ago

Magic Patterns (W23) is one of the fastest-growing design tools in AI, helping product teams turn ideas into interactive, code-backed prototypes in minutes. Alex Danilowicz and his co-founder, both front-end engineers, built Magic Patterns to solve a problem they had themselves: finding a better way to turn ideas into something visual. They were among the first teams building prompt-to-design tools back in 2023. In this episode of Design Review, Alex joins YC’s Aaron Epstein to demo Magic Patterns and its new MagicOS canvas, where teams can bring together prompts, images, PRDs, and other context to explore ideas visually. Then they review a handful of startup websites to break down what makes a site feel “vibe coded,” where founders go wrong, and how to make AI-generated design feel more intentional. 02:11 — From YC Pivot to Product-Market Fit 03:44 — Staying Ahead as AI Design Tools Improve 04:37 — Demo: Designing With Magic Patterns 09:52 — MagicOS 11:23 — Designing With Context on a Canvas 14:50 — How to Get Better Results From AI Design Tools 15:35 — How Far Can AI-Generated Design Go? 18:17 — Website Review 1: Ego 23:59 — Website Review 2: Sentient OS 32:01 — Website Review 3: Cerenovus 36:59 — Website Review 4: Slashy 43:33 — How to Develop Better Design Taste 44:20 — Why Everyone at Magic Patterns Talks to Users 45:07 — Balancing Speed and Design Quality 46:07 — The Future of Design and Magic Patterns
47:42

Magic Patterns (W23) is one of the fastest-growing design tools in AI, helping product teams turn ideas into interactive, code-backed prototypes in minutes. Alex Danilowicz and his co-founder, both front-end engineers, built Magic Patterns to solve a problem they had themselves: finding a better way to turn ideas into something visual. They were among the first teams building prompt-to-design tools back in 2023. In this episode of Design Review, Alex joins YC’s Aaron Epstein to demo Magic Patterns and its new MagicOS canvas, where teams can bring together prompts, images, PRDs, and other context to explore ideas visually. Then they review a handful of startup websites to break down what makes a site feel “vibe coded,” where founders go wrong, and how to make AI-generated design feel more intentional. 02:11 — From YC Pivot to Product-Market Fit 03:44 — Staying Ahead as AI Design Tools Improve 04:37 — Demo: Designing With Magic Patterns 09:52 — MagicOS 11:23 — Designing With Context on a Canvas 14:50 — How to Get Better Results From AI Design Tools 15:35 — How Far Can AI-Generated Design Go? 18:17 — Website Review 1: Ego 23:59 — Website Review 2: Sentient OS 32:01 — Website Review 3: Cerenovus 36:59 — Website Review 4: Slashy 43:33 — How to Develop Better Design Taste 44:20 — Why Everyone at Magic Patterns Talks to Users 45:07 — Balancing Speed and Design Quality 46:07 — The Future of Design and Magic Patterns

Y Combinator

35,565 views • 21 days ago

More founders should care about design in the earliest days of their startup. YC's Aaron Epstein sat down with Raphael Schaad, the Head of Calendar at Notion, to unpack why good design is crucial in making things people want. They discuss how Raphael made the leap from designer to founder, why illustration is an important first step in the creation of new products, and what makes designers uniquely qualified to start a company today.
0:41

More founders should care about design in the earliest days of their startup. YC's Aaron Epstein sat down with Raphael Schaad, the Head of Calendar at Notion, to unpack why good design is crucial in making things people want. They discuss how Raphael made the leap from designer to founder, why illustration is an important first step in the creation of new products, and what makes designers uniquely qualified to start a company today.

Y Combinator

131,497 views • 1 year ago

Even the most successful websites eventually need a redesign. Take Stripe for example. After six years with the same homepage, Stripe recently unveiled a brand new site that reflects how the company has evolved over the past few years. So when is the time right for a new landing page? And what should you prioritize in the redesign? In this episode of Design Review, YC’s Aaron Epstein sat down Stripe’s Head of Design Katie Dill (Katie Dill) to pull the curtain back on their high profile redesign and to discuss how their team is evolving in a world dominated by new AI design tools. 00:30 - The Old Site 05:30 - “What is the point of a website?” 06:00 - Breaking down the new homepage 07:10 - The GDP counter (and how Stripe builds trust) 08:45 - The Bento Box that fixed the homepage 11:37 - Why great design feels effortless 15:40 - Craft, iteration, and getting it right 19:11 - Inside Stripe’s design process 27:10 - How AI is changing design 35:00 - The fight against mediocrity 40:00 - Walking the Store: Stripe’s Secret to Better Product Design
43:36

Even the most successful websites eventually need a redesign. Take Stripe for example. After six years with the same homepage, Stripe recently unveiled a brand new site that reflects how the company has evolved over the past few years. So when is the time right for a new landing page? And what should you prioritize in the redesign? In this episode of Design Review, YC’s Aaron Epstein sat down Stripe’s Head of Design Katie Dill (Katie Dill) to pull the curtain back on their high profile redesign and to discuss how their team is evolving in a world dominated by new AI design tools. 00:30 - The Old Site 05:30 - “What is the point of a website?” 06:00 - Breaking down the new homepage 07:10 - The GDP counter (and how Stripe builds trust) 08:45 - The Bento Box that fixed the homepage 11:37 - Why great design feels effortless 15:40 - Craft, iteration, and getting it right 19:11 - Inside Stripe’s design process 27:10 - How AI is changing design 35:00 - The fight against mediocrity 40:00 - Walking the Store: Stripe’s Secret to Better Product Design

Y Combinator

86,934 views • 6 months ago

These are my essential AI coding skills I use to keep code quality high and not bloated when AI writes and merges my code for me. This is video 5 of 7 in my “how to become a 10x ai-native developer” series, and in the first 4 videos I talked about how I use cloud agents be a 24/7 on call engineer for me that fixes bugs for me while I sleep by using verification skills to verify all the code changes actually work as intended and how they merge the code for me without me reviewing the code, and as a result I have a lot of code being merged without my supervision. I know a lot of you are wondering, how do you keep the code quality high when letting AI write so much code? I do so by deferring to skills to do that. I use the cursor team’s thermo nuclear code quality review (excessive, I know) in conjunction with framework specific tools like a react best practices skill and with , one of my personal favorites, the ponytail skill. Highly recommend you check out the ponytail.dev website which is the home for the skill it is so funny and I’ll show a little screenshot right here, but essentially I have these sets of skills to point out common pitfalls of overly verbose and complicated code and I tell all my coding agents to run these skills before making the PR and sometimes I tell them to run these simplification skills multiple times in a row. Due to the non deterministic nature of LLMs, forcing them to run these simplification skills multiple times allow these models to uncover new simplification methods that it didn’t catch the previous try. #coding #ai #developer
2:33

These are my essential AI coding skills I use to keep code quality high and not bloated when AI writes and merges my code for me. This is video 5 of 7 in my “how to become a 10x ai-native developer” series, and in the first 4 videos I talked about how I use cloud agents be a 24/7 on call engineer for me that fixes bugs for me while I sleep by using verification skills to verify all the code changes actually work as intended and how they merge the code for me without me reviewing the code, and as a result I have a lot of code being merged without my supervision. I know a lot of you are wondering, how do you keep the code quality high when letting AI write so much code? I do so by deferring to skills to do that. I use the cursor team’s thermo nuclear code quality review (excessive, I know) in conjunction with framework specific tools like a react best practices skill and with , one of my personal favorites, the ponytail skill. Highly recommend you check out the ponytail.dev website which is the home for the skill it is so funny and I’ll show a little screenshot right here, but essentially I have these sets of skills to point out common pitfalls of overly verbose and complicated code and I tell all my coding agents to run these skills before making the PR and sometimes I tell them to run these simplification skills multiple times in a row. Due to the non deterministic nature of LLMs, forcing them to run these simplification skills multiple times allow these models to uncover new simplification methods that it didn’t catch the previous try. #coding #ai #developer

YourAverageTechBro

171,500 views • 1 month ago

AI isn't just changing the tools designers use. It's changing the way they think, prototype, and build. In this episode of Design Review, YC Head of Design eve joins Aaron Epstein to share the AI-first workflow she uses to design products, websites, and events. Using projects like Paxel, STATE OF THE ART, and YC Startup School as examples, she explains how coding agents are transforming everything from rapid prototyping and branding to design systems, and why the biggest bottleneck is no longer software. It's imagination. 00:00 - Eve's AI-First Design Workflow 01:27 - Why She Designs With Her Voice 03:44 - Paxel: Spotify Wrapped for Coding Sessions 07:13 - Building Tools for Yourself 11:01 - Turning Coding Transcripts Into Feedback 12:53 - The Story Behind SOTA Zine 16:57 - Designing With Context, Not Prompts 21:07 - How to Get Better AI Design Outputs 23:20 - Building an Interactive Map of San Francisco 25:17 - Behind Startup School's Visual Identity 29:59 - The Future of Design
30:54

AI isn't just changing the tools designers use. It's changing the way they think, prototype, and build. In this episode of Design Review, YC Head of Design eve joins Aaron Epstein to share the AI-first workflow she uses to design products, websites, and events. Using projects like Paxel, STATE OF THE ART, and YC Startup School as examples, she explains how coding agents are transforming everything from rapid prototyping and branding to design systems, and why the biggest bottleneck is no longer software. It's imagination. 00:00 - Eve's AI-First Design Workflow 01:27 - Why She Designs With Her Voice 03:44 - Paxel: Spotify Wrapped for Coding Sessions 07:13 - Building Tools for Yourself 11:01 - Turning Coding Transcripts Into Feedback 12:53 - The Story Behind SOTA Zine 16:57 - Designing With Context, Not Prompts 21:07 - How to Get Better AI Design Outputs 23:20 - Building an Interactive Map of San Francisco 25:17 - Behind Startup School's Visual Identity 29:59 - The Future of Design

Y Combinator

104,011 views • 4 months ago

Cursor Head of Design Ryo Lu (Ryo Lu) has spent his career at the intersection of design and engineering—from building fan sites as a kid to designing products at Stripe, Asana, and Notion. Now he's rethinking how software itself gets made. On this episode of Design Review, Ryo joins YC's Aaron Epstein to break down how great product websites communicate what a company does. They walk through sites from early-stage startups, calling out the small choices in structure, clarity, and brand that help users understand a product instantly— and the ones that get in the way. 00:00 - Intro 01:00 - Crunched 05:30 - Velvet 09:00 - Klavis AI 14:30 - Code Crafters 20:40 - Slashy 22:50 - Freya 26:00 - Finta 30:30 - Vibeflow
35:34

Cursor Head of Design Ryo Lu (Ryo Lu) has spent his career at the intersection of design and engineering—from building fan sites as a kid to designing products at Stripe, Asana, and Notion. Now he's rethinking how software itself gets made. On this episode of Design Review, Ryo joins YC's Aaron Epstein to break down how great product websites communicate what a company does. They walk through sites from early-stage startups, calling out the small choices in structure, clarity, and brand that help users understand a product instantly— and the ones that get in the way. 00:00 - Intro 01:00 - Crunched 05:30 - Velvet 09:00 - Klavis AI 14:30 - Code Crafters 20:40 - Slashy 22:50 - Freya 26:00 - Finta 30:30 - Vibeflow

Y Combinator

172,131 views • 11 months ago

While your team is just getting started vibe coding prototypes, the team at Stripe is vibe coding a full vibe coding platform. Owen Williams ⚡ is a design manager at Stripe who built Protodash - an internal AI prototyping tool that lets designers and PMs spin up real, clickable prototypes in minutes. In this ep he walks through: - why generic AI tools produce "blurple slop" that doesn't match your design system - how he built a full prototyping studio on top of dev boxes with cursor + cc - why more PMs than designers now use Protodash - the design review mode that lets teams ship feedback direct in the app Plus, we talk about getting to the ultimate dream: demos, not memos. ty to our sponsors! 🧠 CESAR - Intelligent automation built for AI 💻 Cursor - The best way to code with AI Full episode on yt:
0:41

While your team is just getting started vibe coding prototypes, the team at Stripe is vibe coding a full vibe coding platform. Owen Williams ⚡ is a design manager at Stripe who built Protodash - an internal AI prototyping tool that lets designers and PMs spin up real, clickable prototypes in minutes. In this ep he walks through: - why generic AI tools produce "blurple slop" that doesn't match your design system - how he built a full prototyping studio on top of dev boxes with cursor + cc - why more PMs than designers now use Protodash - the design review mode that lets teams ship feedback direct in the app Plus, we talk about getting to the ultimate dream: demos, not memos. ty to our sponsors! 🧠 CESAR - Intelligent automation built for AI 💻 Cursor - The best way to code with AI Full episode on yt:

claire vo 🖤

92,220 views • 6 months ago

The best product websites do more than pitch. They explain, guide, and reflect the product itself, and often serve as a company’s first impression. For Design Review, YC’s Aaron Epstein is joined by Karri Saarinen (Karri Saarinen), co-founder & CEO of Linear, to break down how today’s best software companies design their sites. They review examples from Linear, Sprites AI, , UnReal Milk, Confident AI, and Dropback, exploring how structure, motion, and clarity shape not just the user experience, but the brand as well. 00:43 - Authenticity in Branding 02:02 - The Initial Website for Linear 02:57 - Importance of Clear Messaging 03:49 - Be Specific 04:12 - Two Different Descriptions for Startups 07:55 - Brands and Design Evolve Over Time 09:57 - Sprites AI 15:09 - GigaML 22:02 - UnReal Milk 29:57 - Confident AI 34:27 - Talk to Your Ideal Customer 37:22 - Dropback
43:41

The best product websites do more than pitch. They explain, guide, and reflect the product itself, and often serve as a company’s first impression. For Design Review, YC’s Aaron Epstein is joined by Karri Saarinen (Karri Saarinen), co-founder & CEO of Linear, to break down how today’s best software companies design their sites. They review examples from Linear, Sprites AI, , UnReal Milk, Confident AI, and Dropback, exploring how structure, motion, and clarity shape not just the user experience, but the brand as well. 00:43 - Authenticity in Branding 02:02 - The Initial Website for Linear 02:57 - Importance of Clear Messaging 03:49 - Be Specific 04:12 - Two Different Descriptions for Startups 07:55 - Brands and Design Evolve Over Time 09:57 - Sprites AI 15:09 - GigaML 22:02 - UnReal Milk 29:57 - Confident AI 34:27 - Talk to Your Ideal Customer 37:22 - Dropback

Y Combinator

53,692 views • 1 year ago

"We're trying to hire as many new grads as we can. We're finding that a lot of young people are agentmaxxing." - Replit founder Amjad Masad Amjad says that despite the “doom and gloom” around entry-level jobs, this is actually a “golden era” for young people who know how to use AI tools: "The roles are collapsing. We have designers shipping code, engineers shipping design, and salespeople shipping code." "The particular skill is not the bottleneck anymore. It is how ambitious you are, how generative you are, how creative you are, and how good you are at utilizing these tools." "So I think it's really a golden era for a lot of young people coming up right now in the job market. In our time, you would go and interview and become a Java J2EE software engineer doing global migrations. That was your title, right? It's no longer the case. We just want people to come and do things, and I think that's incredibly exciting."
1:49

"We're trying to hire as many new grads as we can. We're finding that a lot of young people are agentmaxxing." - Replit founder Amjad Masad Amjad says that despite the “doom and gloom” around entry-level jobs, this is actually a “golden era” for young people who know how to use AI tools: "The roles are collapsing. We have designers shipping code, engineers shipping design, and salespeople shipping code." "The particular skill is not the bottleneck anymore. It is how ambitious you are, how generative you are, how creative you are, and how good you are at utilizing these tools." "So I think it's really a golden era for a lot of young people coming up right now in the job market. In our time, you would go and interview and become a Java J2EE software engineer doing global migrations. That was your title, right? It's no longer the case. We just want people to come and do things, and I think that's incredibly exciting."

TBPN

47,198 views • 8 months ago

Our designs are affected by the tools we use much more than we think. At a glance, you'd think it's just the designer/artist's taste/skills. But when you look deeper, tools shape how and what you can design. This is why many designers are building their own tools with AI.
0:30

Our designs are affected by the tools we use much more than we think. At a glance, you'd think it's just the designer/artist's taste/skills. But when you look deeper, tools shape how and what you can design. This is why many designers are building their own tools with AI.

Kevin ⨀

12,200 views • 8 months ago

Hilarious that the WNBA is going to hold an actual meeting so they can review what a woman is. How do you become the commissioner of a women’s league but not know what a woman is?
0:26

Hilarious that the WNBA is going to hold an actual meeting so they can review what a woman is. How do you become the commissioner of a women’s league but not know what a woman is?

Derrick Evans

25,915 views • 3 months ago

.Scott Wu to Joe Lonsdale on why Cognition uses AI in job interviews: "One or two years ago, people had this mentality of 'How do we make sure people aren't using AI while we're interviewing them?' And I think that has totally flipped. Honestly, I think that was wrong... If you're asking the question of like, how do we evaluate people on exactly the thing that AI can already do, that seems kind of the wrong. Our interview process has always been... you can use as much AI as you want to use. We're going to give you a few hours. Just build your whole own product surface. A lot of these are projects that, frankly, is like, if you were trying to do this by hand, you would not be able to get done in a few hours. So you kind of have to use AI for this. But in reality, what we actually want to test is, in addition to how familiar you are with these tools, what we actually want to test is, what do you think is the right thing to build? Or how do you make these product decisions? How do you make these trade-offs? How do you decide or collect information about what you should be doing?"
0:58

.Scott Wu to Joe Lonsdale on why Cognition uses AI in job interviews: "One or two years ago, people had this mentality of 'How do we make sure people aren't using AI while we're interviewing them?' And I think that has totally flipped. Honestly, I think that was wrong... If you're asking the question of like, how do we evaluate people on exactly the thing that AI can already do, that seems kind of the wrong. Our interview process has always been... you can use as much AI as you want to use. We're going to give you a few hours. Just build your whole own product surface. A lot of these are projects that, frankly, is like, if you were trying to do this by hand, you would not be able to get done in a few hours. So you kind of have to use AI for this. But in reality, what we actually want to test is, in addition to how familiar you are with these tools, what we actually want to test is, what do you think is the right thing to build? Or how do you make these product decisions? How do you make these trade-offs? How do you decide or collect information about what you should be doing?"

American Optimist

13,182 views • 7 months ago

Welcome to Founder Fridays — a new video series from Notion. We’re sitting down with builders to talk shop: product, design, and the lessons you only learn by doing. Ep 1 features Cron founder Raphael Schaad and Notion PMM Owais Khan. From Chrome extension → beloved calendar app → Notion acquisition.
0:31

Welcome to Founder Fridays — a new video series from Notion. We’re sitting down with builders to talk shop: product, design, and the lessons you only learn by doing. Ep 1 features Cron founder Raphael Schaad and Notion PMM Owais Khan. From Chrome extension → beloved calendar app → Notion acquisition.

Notion

25,720 views • 1 year ago

Nobody is writing 90% of their code using AI. Here's the uncomfortable truth: The real productivity gain from using AI to write code is closer to 10%, nowhere near the 90% people claim. Sundar Pichai said in 2024 that 30% of the new code at Google was AI-generated. However, he went on to admit, during Lex Friedman's podcast, that engineering velocity had only increased by about 10%. AI-generated code isn't free code. It still has to be reviewed, tested, and made production-ready. Optimizing a single step (code generation) doesn't boost output if bottlenecks shift elsewhere (code reviews). It doesn't matter how much code you generate if you can't keep up the review process. The solution: Automate as much as you can the review and verification of your code. I'm working with Sonar, who is sponsoring this post, and they will take care of the code quality and security analysis of your code: • They review over 300B lines of code every single day • They cover reliability, security, and maintainability for your code • You can integrate them into your CI/CD pipeline • You can install them in your IDE (I use their VSCode extension) • Support for more than 30 languages Here is a link so you can check them out:
4:42

Nobody is writing 90% of their code using AI. Here's the uncomfortable truth: The real productivity gain from using AI to write code is closer to 10%, nowhere near the 90% people claim. Sundar Pichai said in 2024 that 30% of the new code at Google was AI-generated. However, he went on to admit, during Lex Friedman's podcast, that engineering velocity had only increased by about 10%. AI-generated code isn't free code. It still has to be reviewed, tested, and made production-ready. Optimizing a single step (code generation) doesn't boost output if bottlenecks shift elsewhere (code reviews). It doesn't matter how much code you generate if you can't keep up the review process. The solution: Automate as much as you can the review and verification of your code. I'm working with Sonar, who is sponsoring this post, and they will take care of the code quality and security analysis of your code: • They review over 300B lines of code every single day • They cover reliability, security, and maintainability for your code • You can integrate them into your CI/CD pipeline • You can install them in your IDE (I use their VSCode extension) • Support for more than 30 languages Here is a link so you can check them out:

Santiago

296,928 views • 1 year ago