Loading video...

Video Failed to Load

There was a problem loading this video. This could be due to a temporary network issue or the video might be unavailable.

Kicking off my favorite week at Gauntlet AI: Adding significant user-facing features to massive legacy codebases. Older programming languages, versioning issues, convoluted templating, funky CI/CD. AI still must write 100% of the code. Challengers have one week.

Austen Allred

443,928 subscribers

32,953 views • 1 year ago •via X (Twitter)

Science & Technology Education Comedy

Anya Rossi• Live Now

Private livecam show

0 Comments

No comments available

Comments from the original post will appear here

Related Videos

Software Engineering Expectations for 2026 - The majority of your code should be written by AI now - Cursor/Codex/Claude Code/Gemini/etc - You should try all the tooling and switch between them, as each one gets an edge over the others depending on the release cycle. - You should be using AI to check the code that is written by AI - Have AI write tests - Have AI read logs - Have AI navigate your browser - I don't do this every time because sometimes it's simple enough to check it myself - You should still skim code changes - This can be a lighter skim on internal tools and a heavier read through on customer facing code - Use AI to help you define specs

Software Engineering Expectations for 2026 - The majority of your code should be written by AI now - Cursor/Codex/Claude Code/Gemini/etc - You should try all the tooling and switch between them, as each one gets an edge over the others depending on the release cycle. - You should be using AI to check the code that is written by AI - Have AI write tests - Have AI read logs - Have AI navigate your browser - I don't do this every time because sometimes it's simple enough to check it myself - You should still skim code changes - This can be a lighter skim on internal tools and a heavier read through on customer facing code - Use AI to help you define specs

Ben Awad

535,633 views • 9 months ago

Hope you are all having a fantastic start to your week, take a look at the video below, covering a 72 hour water only fast starting at the weekend, why Cbd has become a big part of my natural health journey and more. 100’s of you joined me last time and were so supportive of one another. To find out more about the Cbd I use or to purchase take a look at and receive 40 percent off with my code Tiss40. Have a great week one and all. #wateronlyfast #supremcbd #ad #naturalhealth

Hope you are all having a fantastic start to your week, take a look at the video below, covering a 72 hour water only fast starting at the weekend, why Cbd has become a big part of my natural health journey and more. 100’s of you joined me last time and were so supportive of one another. To find out more about the Cbd I use or to purchase take a look at and receive 40 percent off with my code Tiss40. Have a great week one and all. #wateronlyfast #supremcbd #ad #naturalhealth

Matt Le Tissier ✝️

67,155 views • 11 months ago

Martin Odersky (Martin Odersky) is the creator of Scala and I interviewed him to compare different languages designs (Rust vs Zig vs Python vs Scala) and how AI will impact programming languages. In this episode: • Comparing Rust, Zig, Python, and Scala designs • Why its hard to write a compiler • Predictions about how AI will impact software • Why functional programming matters Where to watch: • YouTube - • Spotify - • Apple Podcasts - • Transcript - Thank you to the sponsors of this episode for supporting my work: • WorkOS: makes your app Enterprise Ready with easy to use APIs to add SSO, SCIM, RBAC, and more in just a few lines of code, check them out at • Jira by Atlassian: Get more work done with your favorite agents and models all in one place, check them out at Chapters: 00:00 Intro 00:44 Why care about functional programming 06:35 Why should people learn Scala 09:26 Rust vs Scala 12:42 Rust vs Zig 15:45 Scala vs Python 18:31 The programming languages that influenced him 22:16 How running on the JVM works 26:33 Why writing a compiler is hard 29:19 Why Twitter adopted Scala early on 31:00 How he believes AI will impact programming languages 43:40 Will there be less engineers in ten years 44:34 Top programming languages to learn to grow 46:18 Top technical book recommendation 46:51 Why he chose academia instead of industry 48:28 Reflecting on Scala 55:42 Advice for his younger self 56:33 Outro

Martin Odersky (Martin Odersky) is the creator of Scala and I interviewed him to compare different languages designs (Rust vs Zig vs Python vs Scala) and how AI will impact programming languages. In this episode: • Comparing Rust, Zig, Python, and Scala designs • Why its hard to write a compiler • Predictions about how AI will impact software • Why functional programming matters Where to watch: • YouTube - • Spotify - • Apple Podcasts - • Transcript - Thank you to the sponsors of this episode for supporting my work: • WorkOS: makes your app Enterprise Ready with easy to use APIs to add SSO, SCIM, RBAC, and more in just a few lines of code, check them out at • Jira by Atlassian: Get more work done with your favorite agents and models all in one place, check them out at Chapters: 00:00 Intro 00:44 Why care about functional programming 06:35 Why should people learn Scala 09:26 Rust vs Scala 12:42 Rust vs Zig 15:45 Scala vs Python 18:31 The programming languages that influenced him 22:16 How running on the JVM works 26:33 Why writing a compiler is hard 29:19 Why Twitter adopted Scala early on 31:00 How he believes AI will impact programming languages 43:40 Will there be less engineers in ten years 44:34 Top programming languages to learn to grow 46:18 Top technical book recommendation 46:51 Why he chose academia instead of industry 48:28 Reflecting on Scala 55:42 Advice for his younger self 56:33 Outro

Ryan Peterman

103,578 views • 1 month 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:

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

296,750 views • 1 year ago

Day 3 of getting back to building my gamified workout tracker. (have some AI features) I just tested both Opus 4.8 and GPT-5.5 for the multilingual feature, and Opus 4.8 is still slightly better. It only needed one prompt to solve it. My apps always supports multiple languages because I target multiple markets and don’t want to depend on just one market. Powered by Opus 4.8, Rork, Cursor

Day 3 of getting back to building my gamified workout tracker. (have some AI features) I just tested both Opus 4.8 and GPT-5.5 for the multilingual feature, and Opus 4.8 is still slightly better. It only needed one prompt to solve it. My apps always supports multiple languages because I target multiple markets and don’t want to depend on just one market. Powered by Opus 4.8, Rork, Cursor

Alex Nguyen

14,562 views • 3 months ago

Sam Altman and Dario Amodei just spoke at the UN Security Council, and it's hard to unhear. Amodei: "four years ago AI could barely write a line of code, today it writes most of the code at Anthropic and solves world-famous unsolved math problems." it's moving so fast that Dario went as far as calling AI "the most important global security issue facing the world today." Altman backed it: "we could lose control of the future to AI." the people building the most powerful AI on earth just warned the UN about their own creation. there's a lot of criticism online that they hype the fear because it pays. maybe, but i'd rather over-index on a warning like this than laugh it off, AI can genuinely be dangerous if no one watches it properly.

Sam Altman and Dario Amodei just spoke at the UN Security Council, and it's hard to unhear. Amodei: "four years ago AI could barely write a line of code, today it writes most of the code at Anthropic and solves world-famous unsolved math problems." it's moving so fast that Dario went as far as calling AI "the most important global security issue facing the world today." Altman backed it: "we could lose control of the future to AI." the people building the most powerful AI on earth just warned the UN about their own creation. there's a lot of criticism online that they hype the fear because it pays. maybe, but i'd rather over-index on a warning like this than laugh it off, AI can genuinely be dangerous if no one watches it properly.

Anatoli Kopadze

182,510 views • 5 days ago

Even if AI will write 90% of code. But it won’t replace engineers. Windsurf’s founder explains that even if AI generates most of the code, engineers still spend time reviewing it, debugging issues, designing systems, testing, deploying, and making architectural decisions. Those parts don’t disappear. He brings up Amdahl’s Law to make the point: speeding up one part of the workflow doesn’t dramatically change the total time unless everything else speeds up too. For example, if writing code takes 30 out of 100 total time units, and AI brings it down to 3, the total time still only drops to 73. That’s just a 27% improvement. More productivity doesn’t mean fewer engineers. It just increases the ROI of building tech. And when ROI goes up, companies are more likely to build—and hire more people to do it. Take JPMorgan Chase. They have 50,000+ engineers and a $17B software budget. If each engineer can ship more software, that doesn’t reduce headcount. It raises the cost of not building. Companies like Windsurf and Anthropic are hiring more engineers—not less—despite being at the edge of AI code generation.

Even if AI will write 90% of code. But it won’t replace engineers. Windsurf’s founder explains that even if AI generates most of the code, engineers still spend time reviewing it, debugging issues, designing systems, testing, deploying, and making architectural decisions. Those parts don’t disappear. He brings up Amdahl’s Law to make the point: speeding up one part of the workflow doesn’t dramatically change the total time unless everything else speeds up too. For example, if writing code takes 30 out of 100 total time units, and AI brings it down to 3, the total time still only drops to 73. That’s just a 27% improvement. More productivity doesn’t mean fewer engineers. It just increases the ROI of building tech. And when ROI goes up, companies are more likely to build—and hire more people to do it. Take JPMorgan Chase. They have 50,000+ engineers and a $17B software budget. If each engineer can ship more software, that doesn’t reduce headcount. It raises the cost of not building. Companies like Windsurf and Anthropic are hiring more engineers—not less—despite being at the edge of AI code generation.

Aish

27,268 views • 1 year ago

At the AI Engineer 🔜 NYC 🗽 World Fair, I sat down and dumped my brain on a podcast. Here are my latest ponderoos on these topics… ✨ Why code doesn't need to be readable by a human anymore; it needs to be explainable to one. ✨Why frontier intelligence isn't required for most tasks, and why some of the sharpest engineers I know run 20 concurrent $300/year subscriptions instead of one frontier plan. ✨ Why I haven't hand-written code in over two years, and why Git is perhaps already end of life. ✨ Why porting between programming languages is now nearly free, and what that means for which languages survive.

At the AI Engineer 🔜 NYC 🗽 World Fair, I sat down and dumped my brain on a podcast. Here are my latest ponderoos on these topics… ✨ Why code doesn't need to be readable by a human anymore; it needs to be explainable to one. ✨Why frontier intelligence isn't required for most tasks, and why some of the sharpest engineers I know run 20 concurrent $300/year subscriptions instead of one frontier plan. ✨ Why I haven't hand-written code in over two years, and why Git is perhaps already end of life. ✨ Why porting between programming languages is now nearly free, and what that means for which languages survive.

geoff

33,295 views • 1 month ago

Everyone's talking about vibe coding without looking at code. I was skeptical. I decided to give it a shot on a challenging problem and was blown away by what I could accomplish in 8 hours. I'm not skeptical anymore, but I also do NOT think it kills SaaS Notes: - I tried to replicate some of my favorite features from the Solve-It platform as a jupyter extension - I've tried this many times before, and it didn't work. - I gave my agent specific testing tools that I packaged as skills. I used AI to write the skills. I found the right testing workflow for this Jupyter extension by having AI peruse lots of other extensions and the Jupyter source code. - I had the AI write and maintain a large suite of tests the whole time. I think this was important in keeping the AI on track. - I watched the diffs and the thinking traces as they streamed by. From time to time, I would see something very suspicious like " try ... except: pass" And would stop the AI and tell it to stop this behavior. Then trigger a comprehensive code review using AI. - Most importantly, I don't think this kills SasS at all. Even if I can create software that replicates some of my favorite features, there is an insanely long tail of paper cuts and features I don't want to manage. The models and capabilities are improving so fast that I don't want to constantly tune everything. So I would rather leave that up to people who are focused on that daily and have good taste, with the knowledge that it has been battle tested against many users.

Everyone's talking about vibe coding without looking at code. I was skeptical. I decided to give it a shot on a challenging problem and was blown away by what I could accomplish in 8 hours. I'm not skeptical anymore, but I also do NOT think it kills SaaS Notes: - I tried to replicate some of my favorite features from the Solve-It platform as a jupyter extension - I've tried this many times before, and it didn't work. - I gave my agent specific testing tools that I packaged as skills. I used AI to write the skills. I found the right testing workflow for this Jupyter extension by having AI peruse lots of other extensions and the Jupyter source code. - I had the AI write and maintain a large suite of tests the whole time. I think this was important in keeping the AI on track. - I watched the diffs and the thinking traces as they streamed by. From time to time, I would see something very suspicious like " try ... except: pass" And would stop the AI and tell it to stop this behavior. Then trigger a comprehensive code review using AI. - Most importantly, I don't think this kills SasS at all. Even if I can create software that replicates some of my favorite features, there is an insanely long tail of paper cuts and features I don't want to manage. The models and capabilities are improving so fast that I don't want to constantly tune everything. So I would rather leave that up to people who are focused on that daily and have good taste, with the knowledge that it has been battle tested against many users.

Hamel Husain

49,108 views • 9 months ago

Everyone and their mom is using claude code, so how do you stand out? Well, you learn how to use claude code like a senior software engineer. John Lindquist (AI DX Vercel) joins this week at How I AI to walk us through his flows, hooks, and tools that supercharge his cc instance. You'll learn how to - use mermaid diagrams for context - alias your favorite AI commands - write hooks for code quality We also debate TUI vs IDE, discuss esoteric file formats, and build a couple things live. Whether you're an advanced user or CC or wanting to get there, this is the ep for you. ty ty ty to our awesome sponsors 💼 WorkOS- Make your app enterprise-ready today 🔀 Tines - start building intelligent workflows today Watch it here:

Everyone and their mom is using claude code, so how do you stand out? Well, you learn how to use claude code like a senior software engineer. John Lindquist (AI DX Vercel) joins this week at How I AI to walk us through his flows, hooks, and tools that supercharge his cc instance. You'll learn how to - use mermaid diagrams for context - alias your favorite AI commands - write hooks for code quality We also debate TUI vs IDE, discuss esoteric file formats, and build a couple things live. Whether you're an advanced user or CC or wanting to get there, this is the ep for you. ty ty ty to our awesome sponsors 💼 WorkOS- Make your app enterprise-ready today 🔀 Tines - start building intelligent workflows today Watch it here:

claire vo 🖤

26,050 views • 8 months ago

🚨 SPEED SURVIVOR LAUNCHES 🚨 We’re kicking things off with Seahawks vs. Patriots and live in-game props. It’s a full season of Survivor packed into one game. 🏆 $30,000 guaranteed Week 1 prize pool 💵 The first contest currently has a $4,000 overlay 🎁 Get a 100% deposit match up to $1,000 Sign up using code JD or my link: First contest tonight at 8:20 PM ET! Any questions dm Speed Survivor

🚨 SPEED SURVIVOR LAUNCHES 🚨 We’re kicking things off with Seahawks vs. Patriots and live in-game props. It’s a full season of Survivor packed into one game. 🏆 $30,000 guaranteed Week 1 prize pool 💵 The first contest currently has a $4,000 overlay 🎁 Get a 100% deposit match up to $1,000 Sign up using code JD or my link: First contest tonight at 8:20 PM ET! Any questions dm Speed Survivor

JD 

59,992 views • 21 days ago

Google is releasing updates that will let their AI scan all your photos and it will be used to create highly personalized AI image generations or you, your family, pets and more The AI is going to have access to your Gmail, YouTube, search history, photos, calendar and more. The concerning part is Google has admitted to using user data to improve its models People have screenshots of passwords, credit cards, photos of themselves doing intimate things. And all of that is gonna get uploaded to an AI system that is one of many that is consistently shown to be unreliable and not safe at all when it comes to data privacy Let’s not forget that have data leaks, one happened not too long ago Do we really want AI to have access to all this information and being sent back to these massive companies? You’ll be able to opt out of some of it but for your phone to have access to certain features you’ll need to opt in It always starts out optional, then becomes mandatory

Google is releasing updates that will let their AI scan all your photos and it will be used to create highly personalized AI image generations or you, your family, pets and more The AI is going to have access to your Gmail, YouTube, search history, photos, calendar and more. The concerning part is Google has admitted to using user data to improve its models People have screenshots of passwords, credit cards, photos of themselves doing intimate things. And all of that is gonna get uploaded to an AI system that is one of many that is consistently shown to be unreliable and not safe at all when it comes to data privacy Let’s not forget that have data leaks, one happened not too long ago Do we really want AI to have access to all this information and being sent back to these massive companies? You’ll be able to opt out of some of it but for your phone to have access to certain features you’ll need to opt in It always starts out optional, then becomes mandatory

Wall Street Apes

85,514 views • 2 months ago

Last week I sat down with Ankit and did a brain dump. 1. A software factory is essentially a CNC machine or a woodworking shop. Without training, many people will cut off their hands. 2. Building a true “dark factory” as fully automated software production with no humans in the loop means solving autonomous verification first 3. Code review was mostly broken even before AI happened. 4. Agent maintainability is replacing human maintainability as the real measure of code quality 5. Nobody Knows What Engineering Orgs Will Look Like 6. Programming Languages Will Converge, and the Next One Won't Be for Humans 7. The Craft Is More Important Than Ever

Last week I sat down with Ankit and did a brain dump. 1. A software factory is essentially a CNC machine or a woodworking shop. Without training, many people will cut off their hands. 2. Building a true “dark factory” as fully automated software production with no humans in the loop means solving autonomous verification first 3. Code review was mostly broken even before AI happened. 4. Agent maintainability is replacing human maintainability as the real measure of code quality 5. Nobody Knows What Engineering Orgs Will Look Like 6. Programming Languages Will Converge, and the Next One Won't Be for Humans 7. The Craft Is More Important Than Ever

geoff

12,938 views • 3 months ago

The creator of Ruby on Rails just said programmers may be worse at AI coding than people who cannot code. Lex Fridman asked David Heinemeier Hansson directly. His answer: 100%. Because once the AI handles the implementation, knowing how to write a loop is no longer the rare skill. The valuable skills become: What should this product do? Who is it for? What should version one include? What needs to be removed? What should the AI build first? A traditional programmer may tell the agent exactly how to solve the problem. That experience can become a trap. The agent follows the old path instead of finding a better one. Meanwhile, someone who understands users, products, priorities, and taste can describe the desired result and let the agent choose the route. Programming knowledge still matters when the system breaks. But AI is moving the bottleneck away from writing code. The advantage now belongs to the person who knows what should exist, not merely how to implement it. WATCH FULL PODCAST ON Lex Fridman YT CHANNEL

The creator of Ruby on Rails just said programmers may be worse at AI coding than people who cannot code. Lex Fridman asked David Heinemeier Hansson directly. His answer: 100%. Because once the AI handles the implementation, knowing how to write a loop is no longer the rare skill. The valuable skills become: What should this product do? Who is it for? What should version one include? What needs to be removed? What should the AI build first? A traditional programmer may tell the agent exactly how to solve the problem. That experience can become a trap. The agent follows the old path instead of finding a better one. Meanwhile, someone who understands users, products, priorities, and taste can describe the desired result and let the agent choose the route. Programming knowledge still matters when the system breaks. But AI is moving the bottleneck away from writing code. The advantage now belongs to the person who knows what should exist, not merely how to implement it. WATCH FULL PODCAST ON Lex Fridman YT CHANNEL

Ihtesham Ali

143,004 views • 1 month ago

In our latest Box AI Enterprise Eval, we tested Paul Jankura’s Claude 4 Sonnet and Opus models, now integrated into Box AI, across enterprise Q&A tasks, technical workflows, and advanced coding scenarios—revealing major advancements in developer productivity and content intelligence. AI-assisted coding and development just reached a new milestone! Here's what we discovered: Claude 4 significantly improves understanding, generating, and debugging code across multiple programming languages. Developers can: ↳ Accelerate code generation ↳ Improve debugging ↳ Enhance technical documentation ↳ Build smarter AI agents 👉 Automating Financial Analysis with Code Generation: We evaluated Claude 4 by using the Box AI API to analyze ten complex 10-K financial reports. Claude 4 dynamically generated Python code to fetch file IDs from a Box folder, automating data extraction. Within two minutes, it accurately extracted key company data such as revenues, metrics, and highlights—demonstrating its potential to streamline demanding analytical tasks. 👉 Understanding Enterprise Content: Our evaluation confirms Claude 4 maintains strong performance on enterprise Q&A tasks, effectively extracting precise details from single documents and reliably synthesizing information across multiple sources. This ensures seamless integration of structured and unstructured data alongside powerful coding capabilities. 🔓 Developer-Centric Use Cases Unlocked: Organizations can leverage Claude 4 within Box AI to: ↳ Create custom engineering agents referencing technical documents stored in Box, pulling real-time data from Jira, or finding solutions on Stack Overflow. ↳ Build intelligent technical support bots capable of analyzing user-provided code snippets against internal manuals. ↳ Automate secure code reviews by evaluating repository code (stored in Box) against security policies. ↳ Efficiently migrate legacy systems by translating old codebases into modern languages or platforms. Ready to empower your developers and accelerate innovation? To explore Claude 4 Sonnet and Opus through Box AI Studio and APIs, contact us at ailabs@box.com and request early access today! Learn more:

In our latest Box AI Enterprise Eval, we tested Paul Jankura’s Claude 4 Sonnet and Opus models, now integrated into Box AI, across enterprise Q&A tasks, technical workflows, and advanced coding scenarios—revealing major advancements in developer productivity and content intelligence. AI-assisted coding and development just reached a new milestone! Here's what we discovered: Claude 4 significantly improves understanding, generating, and debugging code across multiple programming languages. Developers can: ↳ Accelerate code generation ↳ Improve debugging ↳ Enhance technical documentation ↳ Build smarter AI agents 👉 Automating Financial Analysis with Code Generation: We evaluated Claude 4 by using the Box AI API to analyze ten complex 10-K financial reports. Claude 4 dynamically generated Python code to fetch file IDs from a Box folder, automating data extraction. Within two minutes, it accurately extracted key company data such as revenues, metrics, and highlights—demonstrating its potential to streamline demanding analytical tasks. 👉 Understanding Enterprise Content: Our evaluation confirms Claude 4 maintains strong performance on enterprise Q&A tasks, effectively extracting precise details from single documents and reliably synthesizing information across multiple sources. This ensures seamless integration of structured and unstructured data alongside powerful coding capabilities. 🔓 Developer-Centric Use Cases Unlocked: Organizations can leverage Claude 4 within Box AI to: ↳ Create custom engineering agents referencing technical documents stored in Box, pulling real-time data from Jira, or finding solutions on Stack Overflow. ↳ Build intelligent technical support bots capable of analyzing user-provided code snippets against internal manuals. ↳ Automate secure code reviews by evaluating repository code (stored in Box) against security policies. ↳ Efficiently migrate legacy systems by translating old codebases into modern languages or platforms. Ready to empower your developers and accelerate innovation? To explore Claude 4 Sonnet and Opus through Box AI Studio and APIs, contact us at [email protected] and request early access today! Learn more:

Box

285,689 views • 1 year ago

People always argue that AI writes terrible code & breaks in a real, large codebase. Well, episode 14 of How I AI will show you how AI can write high quality, production code for engineering teams of 100+ My pal Zach is an eng leader at LaunchDarkly and went from an AI sceptic to driving AI adoption in 6 months. In this ep he shows: 📑 how to structure docs in your repo so you DRY to your AI agents ✅ use AI to burn down tech debt 🙊 use ChatGPT to help you be a less conflict avoidant manager This ep is the “big company” sequel to Ryan Carson’s structured vibe coding ep and not one to miss. Big thanks to our sponsors: 🎩 WorkOS – Make your app enterprise-ready today 🛠️ Maven 🏛 – hands on AI education curated by Lenny Rachitsky and me!

People always argue that AI writes terrible code & breaks in a real, large codebase. Well, episode 14 of How I AI will show you how AI can write high quality, production code for engineering teams of 100+ My pal Zach is an eng leader at LaunchDarkly and went from an AI sceptic to driving AI adoption in 6 months. In this ep he shows: 📑 how to structure docs in your repo so you DRY to your AI agents ✅ use AI to burn down tech debt 🙊 use ChatGPT to help you be a less conflict avoidant manager This ep is the “big company” sequel to Ryan Carson’s structured vibe coding ep and not one to miss. Big thanks to our sponsors: 🎩 WorkOS – Make your app enterprise-ready today 🛠️ Maven 🏛 – hands on AI education curated by Lenny Rachitsky and me!

claire vo 🖤

82,224 views • 1 year ago

LinkedIn just started hiding AI-written posts. And their system catches them 94 percent of the time. But the answer is NOT to stop using AI. They announced this in May. If your post sounds like everyone else's, it doesn't get deleted. It just stops spreading. Your followers see it. Nobody new ever does. They're even flagging the way AI writes. Sentences like "it's not this, it's that"? Flagged. But most people missed one line in that announcement: using AI to HELP you write is totally fine. You just have to make it sound like you. Here are 2 things you can do: One, give your AI your own stuff. Upload your old posts, your client results, your stories, your data, your transcripts. Now instead of pulling generic advice off the internet, it's writing from YOUR experience. In your voice. Two, write about what people care about RIGHT NOW. I check AnswerThePublic to see the exact questions my audience is typing in this week then I write about those. The more you sound like yourself and talk about real problems people face, the more people will want to hear what you have to say.

LinkedIn just started hiding AI-written posts. And their system catches them 94 percent of the time. But the answer is NOT to stop using AI. They announced this in May. If your post sounds like everyone else's, it doesn't get deleted. It just stops spreading. Your followers see it. Nobody new ever does. They're even flagging the way AI writes. Sentences like "it's not this, it's that"? Flagged. But most people missed one line in that announcement: using AI to HELP you write is totally fine. You just have to make it sound like you. Here are 2 things you can do: One, give your AI your own stuff. Upload your old posts, your client results, your stories, your data, your transcripts. Now instead of pulling generic advice off the internet, it's writing from YOUR experience. In your voice. Two, write about what people care about RIGHT NOW. I check AnswerThePublic to see the exact questions my audience is typing in this week then I write about those. The more you sound like yourself and talk about real problems people face, the more people will want to hear what you have to say.

Neil Patel

12,378 views • 1 month ago

I set up Gemini Spark to write my own weekly AI news digest for me, and I'm still stuck on how little effort I had to put in. This is the exact prompt I gave it, just once: "Every Tuesday at 12:15 PM, create a new Doc in my Drive, find the 5 biggest AI stories from that week, and format each one properly." And here's what it actually produces, every week: 1. A new Doc, created and named on its own 2. The 5 biggest AI stories from that week, found and picked automatically 3. A bold headline and a summary for each one 4. The key impact spelled out, not just the news 5. A source link on every single story This runs on a schedule so I never have to think about it again. I didn't ask anything on Tuesday, I just opened the drive and the news digest doc was already there. Just like this, you can use Spark to automate any recurring task.

I set up Gemini Spark to write my own weekly AI news digest for me, and I'm still stuck on how little effort I had to put in. This is the exact prompt I gave it, just once: "Every Tuesday at 12:15 PM, create a new Doc in my Drive, find the 5 biggest AI stories from that week, and format each one properly." And here's what it actually produces, every week: 1. A new Doc, created and named on its own 2. The 5 biggest AI stories from that week, found and picked automatically 3. A bold headline and a summary for each one 4. The key impact spelled out, not just the news 5. A source link on every single story This runs on a schedule so I never have to think about it again. I didn't ask anything on Tuesday, I just opened the drive and the news digest doc was already there. Just like this, you can use Spark to automate any recurring task.

Eyisha Zyer

41,454 views • 1 month ago

Boris Cherny, Head of Claude Code at Anthropic: "I do not prompt Claude anymore. I have loops running that prompt Claude. My job is to write loops." The person who built the most used AI coding tool stopped prompting entirely. Most people using it every day are still typing one request at a time. This Github repo changes that. ↳ Seven production loop patterns with real token cost estimates ↳ CLI that scaffolds your entire loop in five minutes ↳ Starters for Grok, Claude Code, Codex, and Opencode The repo gives you the framework. My article covers the mental shift that makes it actually work.

Boris Cherny, Head of Claude Code at Anthropic: "I do not prompt Claude anymore. I have loops running that prompt Claude. My job is to write loops." The person who built the most used AI coding tool stopped prompting entirely. Most people using it every day are still typing one request at a time. This Github repo changes that. ↳ Seven production loop patterns with real token cost estimates ↳ CLI that scaffolds your entire loop in five minutes ↳ Starters for Grok, Claude Code, Codex, and Opencode The repo gives you the framework. My article covers the mental shift that makes it actually work.

Kanika

20,683 views • 2 months ago

Fresh off the launch of Opus 5, Claude Code creator Boris Cherny (Boris Cherny) joins YC's Diana at Startup School 2026 to talk about what the newest models can do, how Claude Code came to be, and what it means to build products when the underlying capabilities keep accelerating. 00:07 — What Makes Opus 5 Different 02:06 — Solving Prompt Injection 03:21 — Why Claude Code Deleted 80% of Its System Prompt 06:37 — Press Delete on Your AI Product 07:20 — How to Rebuild Your System Prompt 10:30 — Product Overhang and “Unhobbling” AI 14:26 — Give Claude Harder Problems 19:32 — Prompt Engineering Is Changing 21:57 — The Two-Week Claude Code Prompt 24:42 — Running Thousands of AI Agents 30:15 — Coding Is (Almost) Solved 32:20 — What Every CS Student Should Still Learn Anthropic Claude

Fresh off the launch of Opus 5, Claude Code creator Boris Cherny (Boris Cherny) joins YC's Diana at Startup School 2026 to talk about what the newest models can do, how Claude Code came to be, and what it means to build products when the underlying capabilities keep accelerating. 00:07 — What Makes Opus 5 Different 02:06 — Solving Prompt Injection 03:21 — Why Claude Code Deleted 80% of Its System Prompt 06:37 — Press Delete on Your AI Product 07:20 — How to Rebuild Your System Prompt 10:30 — Product Overhang and “Unhobbling” AI 14:26 — Give Claude Harder Problems 19:32 — Prompt Engineering Is Changing 21:57 — The Two-Week Claude Code Prompt 24:42 — Running Thousands of AI Agents 30:15 — Coding Is (Almost) Solved 32:20 — What Every CS Student Should Still Learn Anthropic Claude

Y Combinator

86,720 views • 2 months ago