Loading video...

Video Failed to Load

Go Home

Software is dead?! Eragon’s Josh Sirota says that logging into a SaaS platform will soon feel like buying a CD instead of streaming your favorite song. Users just want the output now, with no more worrying about the interface. The panel debates whether this means software developers will disappear,...

ThisWeeknAI's profile picture

This Week in AI

15,257 subscribers

259,365 views • 7 days ago •via X (Twitter)

Science & TechnologyEducationNews & Politics
LIVE

Anya Rossi• Live Now

Private livecam show

0 Comments

No comments available

Comments from the original post will appear here

Related Videos

We're entering a new era of software where a single person, working with AI agents, can build products that previously required entire teams. In this episode of the Lightcone Podcast, they break down the rise of AI coding agents, "tokenmaxxing", and the emerging workflows behind tools like Claude Code and OpenClaw. They discuss why AI systems today feel less like productivity tools and more like collaborators, why the future of AI should be personal and user-controlled, and how founders are starting to build software in completely new ways. 00:00 — Will you control your AI? 00:47 — Coding again after 13 years 01:56 — Rebuilding a startup with Claude Code 05:50 — Software that thinks like a journalist 07:09 — The rise of “tokenmaxxing” 10:07 — The accidental creation of GStack 14:21 — The workflow behind 400x output 20:59 — Thin Harness, Fat Skills 24:35 — AI agents are like Ferraris 27:12 — The future of personal AI 38:37 — Buying back time with tokens
41:29

We're entering a new era of software where a single person, working with AI agents, can build products that previously required entire teams. In this episode of the Lightcone Podcast, they break down the rise of AI coding agents, "tokenmaxxing", and the emerging workflows behind tools like Claude Code and OpenClaw. They discuss why AI systems today feel less like productivity tools and more like collaborators, why the future of AI should be personal and user-controlled, and how founders are starting to build software in completely new ways. 00:00 — Will you control your AI? 00:47 — Coding again after 13 years 01:56 — Rebuilding a startup with Claude Code 05:50 — Software that thinks like a journalist 07:09 — The rise of “tokenmaxxing” 10:07 — The accidental creation of GStack 14:21 — The workflow behind 400x output 20:59 — Thin Harness, Fat Skills 24:35 — AI agents are like Ferraris 27:12 — The future of personal AI 38:37 — Buying back time with tokens

Y Combinator

67,145 views • 3 months ago

Jensen Huang just said this is the greatest era in history to build software. AI agents will not kill software. They will do the exact opposite: create a massive new wave of software demand. at NVIDIA GTC Taipei 2026 "Click and type. We now replace that with explaining to the AI what we want, our intent, and the AI generates the code or uses tools to produce the necessary output. This is how computers are going to work in the future. This is Agentic AI. For two years, we've been building toward this, and now it has arrived. One of the big breakthroughs, of course, is tool use. A lot of people have said, “Jensen, AI is coming. Agentic AI is coming. Therefore, all the software companies are going to go out of business.” This is exactly the opposite. Because there are going to be so many agents, the world is no longer limited by the number of people. Therefore, those agents are going to use more tools than ever. This is actually an incredible time to be a software company. But the software has to be presented to the agent in a way that the agent can use it. This is a big breakthrough. And in fact, what we have done, as you know, what Nvidia’s treasure..." ---- From 'NVIDIA' YT channel (link in comment)
0:59

Jensen Huang just said this is the greatest era in history to build software. AI agents will not kill software. They will do the exact opposite: create a massive new wave of software demand. at NVIDIA GTC Taipei 2026 "Click and type. We now replace that with explaining to the AI what we want, our intent, and the AI generates the code or uses tools to produce the necessary output. This is how computers are going to work in the future. This is Agentic AI. For two years, we've been building toward this, and now it has arrived. One of the big breakthroughs, of course, is tool use. A lot of people have said, “Jensen, AI is coming. Agentic AI is coming. Therefore, all the software companies are going to go out of business.” This is exactly the opposite. Because there are going to be so many agents, the world is no longer limited by the number of people. Therefore, those agents are going to use more tools than ever. This is actually an incredible time to be a software company. But the software has to be presented to the agent in a way that the agent can use it. This is a big breakthrough. And in fact, what we have done, as you know, what Nvidia’s treasure..." ---- From 'NVIDIA' YT channel (link in comment)

Rohan Paul

16,584 views • 2 months ago

What if we're actually in the middle of the third golden age of software engineering? This is what Grady Booch sees happening. If you are anxious about the state of the industry, you want to watch/listen to Grady's longer-term perspective and stories. Watch the full episode here: 00:00 Intro 01:58 The first golden age of software engineering 18:59 The software crisis 33:01 The second golden age of software engineering 42:21 Y2K and the Dotcom crash 45:47 Early AI 47:34 The third golden age of software engineering 51:48 Why software engineers will very much be needed 58:46 Grady responds to Dario Amodei 1:06:54 New skills engineers will need to succeed 1:10:04 Resources for studying complex systems 1:14:33 How to thrive during periods of change Brought to you by: • Statsig — ⁠ The unified platform for flags, analytics, experiments, and more. • Sonar – The makers of SonarQube, the industry standard for automated code review. Join me online at the Sonar Summit on March 3rd, where I talk about practical tactics for the AI era. • WorkOS – Everything you need to make your app enterprise-ready.
1:17:58

What if we're actually in the middle of the third golden age of software engineering? This is what Grady Booch sees happening. If you are anxious about the state of the industry, you want to watch/listen to Grady's longer-term perspective and stories. Watch the full episode here: 00:00 Intro 01:58 The first golden age of software engineering 18:59 The software crisis 33:01 The second golden age of software engineering 42:21 Y2K and the Dotcom crash 45:47 Early AI 47:34 The third golden age of software engineering 51:48 Why software engineers will very much be needed 58:46 Grady responds to Dario Amodei 1:06:54 New skills engineers will need to succeed 1:10:04 Resources for studying complex systems 1:14:33 How to thrive during periods of change Brought to you by: • Statsig — ⁠ The unified platform for flags, analytics, experiments, and more. • Sonar – The makers of SonarQube, the industry standard for automated code review. Join me online at the Sonar Summit on March 3rd, where I talk about practical tactics for the AI era. • WorkOS – Everything you need to make your app enterprise-ready.

Gergely Orosz

86,896 views • 6 months ago

Some personal hot takes from AI: engineer Miami follows... 1. Software development is a dead-end profession because anyone can be a software developer now. 2. Anyone can use Cursor or any other tool and generate code. Being a coder and being a software engineer are different. 3. Computers used to be gated; now everyone has the power to make computers malleable. Everyone is a software developer now, but that does not mean they are software engineers 4. If you cannot demonstrate how a coding agent works, you are just a consumer and have imposed an artificial glass ceiling on your career as a software engineer. 5. If you are curious, you will have a job. If you have not been curious in the last two years, you are replaceable. 6. SaaS per-seat economics may become unstable as customers need fewer people to achieve results, prompting founders to think about new unit economics 7. Most companies will take two or three years (or more!) to figure out AI transformation. 8. Some companies are already building AI native teams of five to ten people who can build with the grain of AI 9. There will be an explosion in the number of software developers. Software development is now essentially free, and tokens are cheaper than humans 10. Not enough engineers know what it means to be a product engineer 11. JIRA ticket monkeys are cooked 12. If your company has banned AI, you should quit that company 13. AI is more like a musical instrument than just a tool play with it, make discoveries, build intuition learn where AI is good and where it fails
14:55

Some personal hot takes from AI: engineer Miami follows... 1. Software development is a dead-end profession because anyone can be a software developer now. 2. Anyone can use Cursor or any other tool and generate code. Being a coder and being a software engineer are different. 3. Computers used to be gated; now everyone has the power to make computers malleable. Everyone is a software developer now, but that does not mean they are software engineers 4. If you cannot demonstrate how a coding agent works, you are just a consumer and have imposed an artificial glass ceiling on your career as a software engineer. 5. If you are curious, you will have a job. If you have not been curious in the last two years, you are replaceable. 6. SaaS per-seat economics may become unstable as customers need fewer people to achieve results, prompting founders to think about new unit economics 7. Most companies will take two or three years (or more!) to figure out AI transformation. 8. Some companies are already building AI native teams of five to ten people who can build with the grain of AI 9. There will be an explosion in the number of software developers. Software development is now essentially free, and tokens are cheaper than humans 10. Not enough engineers know what it means to be a product engineer 11. JIRA ticket monkeys are cooked 12. If your company has banned AI, you should quit that company 13. AI is more like a musical instrument than just a tool play with it, make discoveries, build intuition learn where AI is good and where it fails

geoff

65,789 views • 1 month ago

Claude Cowork, Mythos, and the Future of Software: my conversation with Felix Rieseberg, who leads Cowork at Anthropic 00:00 Intro 01:53 Claude Mythos Preview and the “step-function change” 06:16 Why Anthropic is treating Mythos differently 11:19 The real story behind Claude Cowork’s “10-day” build 12:42 Why Anthropic realized Claude Code needed a non-technical version 15:44 What Claude Cowork actually is 17:03 Under the hood: virtual machines, tools, skills 18:36 Where Cowork’s memory actually lives 19:26 How Cowork connects to files, apps, and the internet 20:45 Why Felix thinks the local computer is under-appreciated 24:49 Trust: how do you get users comfortable with AI agents? 28:45 What UX actually means for AI agents 31:27 Anthropic Cowork's roadmap is only one month long 34:12 Building 100 prototypes 35:10 If execution is free, what becomes the bottleneck? 37:25 Does it come down to taste? 40:12 The hardest part of building Claude Cowork 41:43 Advice for founders building AI agents 44:21 SaaSpocalypse: what’s left for software startups 49:30 Where AI agents are going next 51:20 Regulated industries and enterprise adoption 54:15 Hot takes: what's underrated, overrated, and what Felix would build today
58:00

Claude Cowork, Mythos, and the Future of Software: my conversation with Felix Rieseberg, who leads Cowork at Anthropic 00:00 Intro 01:53 Claude Mythos Preview and the “step-function change” 06:16 Why Anthropic is treating Mythos differently 11:19 The real story behind Claude Cowork’s “10-day” build 12:42 Why Anthropic realized Claude Code needed a non-technical version 15:44 What Claude Cowork actually is 17:03 Under the hood: virtual machines, tools, skills 18:36 Where Cowork’s memory actually lives 19:26 How Cowork connects to files, apps, and the internet 20:45 Why Felix thinks the local computer is under-appreciated 24:49 Trust: how do you get users comfortable with AI agents? 28:45 What UX actually means for AI agents 31:27 Anthropic Cowork's roadmap is only one month long 34:12 Building 100 prototypes 35:10 If execution is free, what becomes the bottleneck? 37:25 Does it come down to taste? 40:12 The hardest part of building Claude Cowork 41:43 Advice for founders building AI agents 44:21 SaaSpocalypse: what’s left for software startups 49:30 Where AI agents are going next 51:20 Regulated industries and enterprise adoption 54:15 Hot takes: what's underrated, overrated, and what Felix would build today

Matt Turck

80,718 views • 4 months ago

In this episode of the Lightcone Podcast, we sat down with Mukund Jha and Madhav Jha, the founders of Emergent - an AI platform that lets anyone build and ship production-ready software. In just eight months, users have created more than 7 million apps on Emergent, with the number doubling in just the last 45 days. We discuss how they built one of the most powerful AI coding agents, why they focused on non-technical users and what it's like building for a global audience from India. 00:00 - Intro 01:06 - What Is Emergent? 01:18 - Founder Backstory 02:09 - From AI Testing to General Coding Agents 02:52 - Getting Ahead of the Market 04:18 - The Pivot to Non-Technical Users 05:22 - Why Second Movers Can Win in AI 09:04 - Building for Production, Not Just Prototypes 18:21 - Live Demo: Building Apps with Emergent 24:40 - How Emergent Hires and Runs a Lean Team 29:04 - Is SaaS Dead? The Rise of Personalized Software 34:04 - The Future: Niche Apps, Solo Builders and AI Agency
39:32

In this episode of the Lightcone Podcast, we sat down with Mukund Jha and Madhav Jha, the founders of Emergent - an AI platform that lets anyone build and ship production-ready software. In just eight months, users have created more than 7 million apps on Emergent, with the number doubling in just the last 45 days. We discuss how they built one of the most powerful AI coding agents, why they focused on non-technical users and what it's like building for a global audience from India. 00:00 - Intro 01:06 - What Is Emergent? 01:18 - Founder Backstory 02:09 - From AI Testing to General Coding Agents 02:52 - Getting Ahead of the Market 04:18 - The Pivot to Non-Technical Users 05:22 - Why Second Movers Can Win in AI 09:04 - Building for Production, Not Just Prototypes 18:21 - Live Demo: Building Apps with Emergent 24:40 - How Emergent Hires and Runs a Lean Team 29:04 - Is SaaS Dead? The Rise of Personalized Software 34:04 - The Future: Niche Apps, Solo Builders and AI Agency

Y Combinator

107,673 views • 5 months ago

I went to Miami to chat with dax, co-founder of OpenCode. We talked about the future of software engineering, coding agents, and why open source matters more now than ever. Timestamps: 0:00 Intro 5:30 Miami vs San Francisco tech scene 15:05 OpenCode origin story, scaling while open-source 25:03 OpenCode vs. Anthropic: owning models, open-source AI 33:36 AI hardware shortages, predicting the future 42:15 The bet of open-weight models, China vs. US 48:34 Why inference is hard, economics of intelligence 55:36 Will developers be automated? Software engineering as a craft 1:11:02 Advice to founders, building in public, marketing I had so much fun making this with Lan. Enjoy!
1:29:53

I went to Miami to chat with dax, co-founder of OpenCode. We talked about the future of software engineering, coding agents, and why open source matters more now than ever. Timestamps: 0:00 Intro 5:30 Miami vs San Francisco tech scene 15:05 OpenCode origin story, scaling while open-source 25:03 OpenCode vs. Anthropic: owning models, open-source AI 33:36 AI hardware shortages, predicting the future 42:15 The bet of open-weight models, China vs. US 48:34 Why inference is hard, economics of intelligence 55:36 Will developers be automated? Software engineering as a craft 1:11:02 Advice to founders, building in public, marketing I had so much fun making this with Lan. Enjoy!

Madison Kanna

267,359 views • 1 month ago

Marc Benioff just exposed the biggest hypocrisy in the AI boom. The companies building the AI that’s supposed to kill software are some of Salesforce’s largest customers. Benioff: “The AI companies love our products and they can’t buy enough of them. They’re some of our largest customers now: Anthropic, OpenAI, Google, Amazon, you name it.” Let that land. The most advanced AI labs on earth. The companies with more engineering talent and compute than anyone. The ones building the technology that analysts say will make traditional software obsolete. Still buying traditional software. At scale. Benioff: “No one has a company that’s running entirely on a large language model because it’s not real.” Not because they haven’t tried. Because an LLM is not a foundation. It’s a feature. Benioff: “Yeah, Minority Report, I watched the movie. Great guys, fantastic. But I’m in the present-moment reality right now. We’re living in this world. This is 2026.” The analysts writing reports about fully autonomous AI companies have never had to run one. Benioff is running one of the largest enterprise software companies on earth. The gap between those two perspectives is where billions of dollars are being misallocated. Benioff: “How are we doing our financials, our HR, our customer information? How are we doing all of these aspects of our business?” A neural network that hallucinates cannot execute a financial transaction that has to be right every single time. Cannot secure customer data with zero tolerance for error. Cannot provide the determinism that every real business runs on. Benioff: “We need the determinism, and the programmability, and the security, and the sharing.” AI doesn’t replace those requirements. It sits on top of them. Benioff: “I think the software industry is going to be bigger and broader and do more this year than ever before.” The future isn’t AI replacing software. It’s AI making software exponentially more powerful. The smartest people building the future already know this. They’re the ones still buying the software.
2:27

Marc Benioff just exposed the biggest hypocrisy in the AI boom. The companies building the AI that’s supposed to kill software are some of Salesforce’s largest customers. Benioff: “The AI companies love our products and they can’t buy enough of them. They’re some of our largest customers now: Anthropic, OpenAI, Google, Amazon, you name it.” Let that land. The most advanced AI labs on earth. The companies with more engineering talent and compute than anyone. The ones building the technology that analysts say will make traditional software obsolete. Still buying traditional software. At scale. Benioff: “No one has a company that’s running entirely on a large language model because it’s not real.” Not because they haven’t tried. Because an LLM is not a foundation. It’s a feature. Benioff: “Yeah, Minority Report, I watched the movie. Great guys, fantastic. But I’m in the present-moment reality right now. We’re living in this world. This is 2026.” The analysts writing reports about fully autonomous AI companies have never had to run one. Benioff is running one of the largest enterprise software companies on earth. The gap between those two perspectives is where billions of dollars are being misallocated. Benioff: “How are we doing our financials, our HR, our customer information? How are we doing all of these aspects of our business?” A neural network that hallucinates cannot execute a financial transaction that has to be right every single time. Cannot secure customer data with zero tolerance for error. Cannot provide the determinism that every real business runs on. Benioff: “We need the determinism, and the programmability, and the security, and the sharing.” AI doesn’t replace those requirements. It sits on top of them. Benioff: “I think the software industry is going to be bigger and broader and do more this year than ever before.” The future isn’t AI replacing software. It’s AI making software exponentially more powerful. The smartest people building the future already know this. They’re the ones still buying the software.

Dustin

203,575 views • 5 months ago

AI has changed software engineering more in the last 3 years than it has changed in the previous 30. What’s needed is not a debate about whether it’s going away—instead it’s a serious discussion about its future: What are the new primitives, techniques, and best practices for software engineering in the age of AI. That’s why I brought Scott Wu (Scott Wu) on AI & I. He’s the founder of Cognition, the company behind the world’s first autonomous AI coding agent, Devin. Cognition got to $73M ARR in less than 2 years—and they just acquired Windsurf to accelerate their growth. I had Scott on the show to talk about where the programming goes from here. We get into: - What the new tools and workflows are for AI engineers. In the near term, Scott sees software engineering defined by a spectrum of tools. At one end are AI features that speed up coding, like tab complete; at the other are agentic systems, like Devin, that can take on tasks independently. Until engineers can operate entirely at the higher layer of abstraction, he argues, both are essential. - Why Scott thinks AGI is already here. By the benchmarks of a decade ago—passing the Turing test, solving hard math problems, and operating agentically—AGI is already here. The line keeps moving, he argues, because humans constantly redefine work around what machines can’t yet do. - Why developers will turn into product architects. Scott sees the long-term future of software engineering as a steady climb up the ladder of abstraction. Just as programming went from assembly to languages like Python and JavaScript, he thinks the future is humans focusing on the product, while AI agents execute. - How Devin stacks up against Anthropic’s Claude Code. Scott credits Claude Code’s success to great product design and the models becoming capable enough to support autonomous workflows. But according to him, the CLI itself isn’t the breakthrough, it’s how a tool fits into a developer’s workflow. Claude Code’s paradigm is that the AI is you, taking the wheel of your computer, he says, while Devin is like the engineer sitting beside you: it runs in its own cloud environment, manages the repo, and improves over time at testing and refining code. This episode of Every 📧’s AI & I is a must-watch for anyone interested in the brass tacks of how AI changes the future of programming. Watch below! Timestamps: Introduction: 00:02:02 Why Scott thinks AGI is here: 00:02:32 Scott’s personal journey as a founder: 00:09:27 Why the fundamentals of computer science still matter: 00:16:55 How the future of programming will evolve: 00:22:30 A new workflow for the AI-first software engineer: 00:26:50 How Devin stacks up against Claude Code: 00:29:33 Reinforcement learning to build better coding agents: 00:40:05 What excites Scott about AI beyond Cognition: 00:50:05
53:21

AI has changed software engineering more in the last 3 years than it has changed in the previous 30. What’s needed is not a debate about whether it’s going away—instead it’s a serious discussion about its future: What are the new primitives, techniques, and best practices for software engineering in the age of AI. That’s why I brought Scott Wu (Scott Wu) on AI & I. He’s the founder of Cognition, the company behind the world’s first autonomous AI coding agent, Devin. Cognition got to $73M ARR in less than 2 years—and they just acquired Windsurf to accelerate their growth. I had Scott on the show to talk about where the programming goes from here. We get into: - What the new tools and workflows are for AI engineers. In the near term, Scott sees software engineering defined by a spectrum of tools. At one end are AI features that speed up coding, like tab complete; at the other are agentic systems, like Devin, that can take on tasks independently. Until engineers can operate entirely at the higher layer of abstraction, he argues, both are essential. - Why Scott thinks AGI is already here. By the benchmarks of a decade ago—passing the Turing test, solving hard math problems, and operating agentically—AGI is already here. The line keeps moving, he argues, because humans constantly redefine work around what machines can’t yet do. - Why developers will turn into product architects. Scott sees the long-term future of software engineering as a steady climb up the ladder of abstraction. Just as programming went from assembly to languages like Python and JavaScript, he thinks the future is humans focusing on the product, while AI agents execute. - How Devin stacks up against Anthropic’s Claude Code. Scott credits Claude Code’s success to great product design and the models becoming capable enough to support autonomous workflows. But according to him, the CLI itself isn’t the breakthrough, it’s how a tool fits into a developer’s workflow. Claude Code’s paradigm is that the AI is you, taking the wheel of your computer, he says, while Devin is like the engineer sitting beside you: it runs in its own cloud environment, manages the repo, and improves over time at testing and refining code. This episode of Every 📧’s AI & I is a must-watch for anyone interested in the brass tacks of how AI changes the future of programming. Watch below! Timestamps: Introduction: 00:02:02 Why Scott thinks AGI is here: 00:02:32 Scott’s personal journey as a founder: 00:09:27 Why the fundamentals of computer science still matter: 00:16:55 How the future of programming will evolve: 00:22:30 A new workflow for the AI-first software engineer: 00:26:50 How Devin stacks up against Claude Code: 00:29:33 Reinforcement learning to build better coding agents: 00:40:05 What excites Scott about AI beyond Cognition: 00:50:05

Dan Shipper 📧

35,342 views • 11 months ago

Software is eating labor & moats still matter: AI can do cheaply what has never been worth a person's time. Whole verticals have opened up, and unlike in previous product cycles, AI can actually complete work end-to-end. a16z GPs David Haber, Alex Rampell, and Erik Torenberg sat down for a conversation on how AI changed software and what fundamentals still hold true. They cover why moats still matter, the "greenfield strategies" that AI makes possible, the difference between differentiation & defensibility, why context is king, and more. 0:00 Intro 1:12 Why moats still matter 8:48 Why you won't vibecode Microsoft 10:09 The Goldilocks zone of pricing 11:21 Greenfield strategies 16:22 Steel man: Brand and velocity as moats 17:44 "Context is king" 19:58 Feature vs. product vs. company 27:05 Platform risk: Will they compete or tax you? 35:26 Will AI consolidate to winner-take-most? 39:16 Why Dropbox survived 44:06 Why AI is different: It's consensus 48:18 Jobs won't disappear – $1 tasks will explode David Haber Alex Rampell Erik Torenberg
50:44

Software is eating labor & moats still matter: AI can do cheaply what has never been worth a person's time. Whole verticals have opened up, and unlike in previous product cycles, AI can actually complete work end-to-end. a16z GPs David Haber, Alex Rampell, and Erik Torenberg sat down for a conversation on how AI changed software and what fundamentals still hold true. They cover why moats still matter, the "greenfield strategies" that AI makes possible, the difference between differentiation & defensibility, why context is king, and more. 0:00 Intro 1:12 Why moats still matter 8:48 Why you won't vibecode Microsoft 10:09 The Goldilocks zone of pricing 11:21 Greenfield strategies 16:22 Steel man: Brand and velocity as moats 17:44 "Context is king" 19:58 Feature vs. product vs. company 27:05 Platform risk: Will they compete or tax you? 35:26 Will AI consolidate to winner-take-most? 39:16 Why Dropbox survived 44:06 Why AI is different: It's consensus 48:18 Jobs won't disappear – $1 tasks will explode David Haber Alex Rampell Erik Torenberg

a16z

61,997 views • 8 months ago

Andrew Ng, co-founder of Google Brain and Coursera, on the worst career advice being given about AI right now: He doesn't mince words about what he's hearing from supposed experts: "As early as earlier this year and certainly last year, there are a few people advising others to stop learning to write code because AI will automate it." His reasoning is rooted in a historical pattern most people miss: "As something becomes easier, more people should do it, not fewer. When the world moved from assembly language to COBOL, there were actually articles saying, 'Well, we now have COBOL. Programming is so easier. Looks like we don't need programmers anymore.' But the opposite happened." Andrew believes the same thing is happening now with AI-assisted coding: "As we now have AI assisted coding, a lot more people should be coding. And I think the demand for software, custom software, has no practical ceiling. So the cost of software engineering comes down, which it is, we'll just get more and more great software out in the world." But here's where the advice gets uncomfortable for experienced engineers. Andrew Ng is honest about what he's seeing on the ground: "It is true that a fresh college grad that is really on top of AI will outperform a full stack engineer with 10 years of experience that is still doing things they were back in 2022, 3 years ago before GenAI." However, there's a nuance most people miss when they hear that stereotype: "The other piece that is less well appreciated is the best engineers I know are not fresh college grads. They're actually very experienced engineers that deeply understand architecture and the conceptual framework of how to think about computers and additionally are on top of AI and on top of these AI skills."
1:45

Andrew Ng, co-founder of Google Brain and Coursera, on the worst career advice being given about AI right now: He doesn't mince words about what he's hearing from supposed experts: "As early as earlier this year and certainly last year, there are a few people advising others to stop learning to write code because AI will automate it." His reasoning is rooted in a historical pattern most people miss: "As something becomes easier, more people should do it, not fewer. When the world moved from assembly language to COBOL, there were actually articles saying, 'Well, we now have COBOL. Programming is so easier. Looks like we don't need programmers anymore.' But the opposite happened." Andrew believes the same thing is happening now with AI-assisted coding: "As we now have AI assisted coding, a lot more people should be coding. And I think the demand for software, custom software, has no practical ceiling. So the cost of software engineering comes down, which it is, we'll just get more and more great software out in the world." But here's where the advice gets uncomfortable for experienced engineers. Andrew Ng is honest about what he's seeing on the ground: "It is true that a fresh college grad that is really on top of AI will outperform a full stack engineer with 10 years of experience that is still doing things they were back in 2022, 3 years ago before GenAI." However, there's a nuance most people miss when they hear that stereotype: "The other piece that is less well appreciated is the best engineers I know are not fresh college grads. They're actually very experienced engineers that deeply understand architecture and the conceptual framework of how to think about computers and additionally are on top of AI and on top of these AI skills."

Big Brain AI

211,593 views • 2 months ago

I asked Dan Martell to walk me through every level of making money with AI. He gave me the most simple, practical advice I've ever heard on this subject. Level 1 - Making $0 - $100k Level 2 - Making $1m - $10m Level 3 - Building a $10m++ enterprise. 0:00 Only 5% of the World Has Ever Paid for AI 0:46 The Easiest Thing to Sell With AI Right Now 1:56 The Marcus and Sophie Framework 4:24 Theory of Constraints (Right Problem to Solve) 5:33 What Is the Number One Business Constraint 7:13 How to Leave Your Job and Go All In 8:27 Business Is Simple Find a Problem and Solve It 9:08 Stop Getting Ready to Get Ready 9:33 The Sarah Story One Text and $10K 9:53 Pull Up Your Phone and Message Your Contacts 11:05 Dan's Son Gets His First Client at $800/Month 12:41 Best Employee vs. Best Employer 13:59 What Other Services Can You Sell With AI 14:44 Sales Is Not Talking It's Asking 17:01 What to Do When You Hate Your Business 18:40 Pain and Pleasure Are the Only Two Motivators 19:13 They Haven't Made It a Must Yet 20:29 Make It a Must Not a Nice to Have 21:06 The Jen Story and the Gasping Moment 22:17 How to Find Your First 10 to 15 Clients 28:38 The Personal Brand Play 33:06 Vision Is What AI Cannot Do 34:55 Hard for Computers Easy for Humans 36:13 Level 2 Making Your First Million With AI 37:18 The Replacement Ladder Framework 37:39 Admin First Then Delivery Then Marketing 39:09 Why Marketing Is the Biggest AI Category 39:32 Why You Should Keep Sales for Yourself 40:00 Level 5 Leadership and AI Agents 41:41 What a Fully AI Systems Business Looks Like 43:13 The Gym Owner With Three Locations 46:16 Shutting Down the Company for Two Days 46:37 Teaching the Whole Team to Code in Claude 49:28 Wayne the 62 Year Old Who Made $12K a Month 52:38 I Only Share What Actually Works 53:21 Whisper Flow and Talking to Your AI 56:41 Claude Chat Claude Coworker and Claude Code 57:57 The Claude Browser Extension 58:49 Claude Code Is Not Just for Developers 1:00:06 How to Migrate Your AI Memory Across Tools 1:01:08 Level 3 $1M to $10M and the Brand Play 1:02:05 Nobody Buys AI They Buy Trust 1:03:25 Brand Is Association and Association Is Trust 1:05:12 A Million Followers Is $10M in Activated Revenue 1:07:03 How to Keep AI From Becoming Slop 1:07:42 Human in the Loop 1:08:16 The 10 80 10 Rule and Why AI Is Now the 80 1:10:01 The Team FIRED Themselves 1:11:45 Dan's Free AI Curriculum for Your Team
1:13:20

I asked Dan Martell to walk me through every level of making money with AI. He gave me the most simple, practical advice I've ever heard on this subject. Level 1 - Making $0 - $100k Level 2 - Making $1m - $10m Level 3 - Building a $10m++ enterprise. 0:00 Only 5% of the World Has Ever Paid for AI 0:46 The Easiest Thing to Sell With AI Right Now 1:56 The Marcus and Sophie Framework 4:24 Theory of Constraints (Right Problem to Solve) 5:33 What Is the Number One Business Constraint 7:13 How to Leave Your Job and Go All In 8:27 Business Is Simple Find a Problem and Solve It 9:08 Stop Getting Ready to Get Ready 9:33 The Sarah Story One Text and $10K 9:53 Pull Up Your Phone and Message Your Contacts 11:05 Dan's Son Gets His First Client at $800/Month 12:41 Best Employee vs. Best Employer 13:59 What Other Services Can You Sell With AI 14:44 Sales Is Not Talking It's Asking 17:01 What to Do When You Hate Your Business 18:40 Pain and Pleasure Are the Only Two Motivators 19:13 They Haven't Made It a Must Yet 20:29 Make It a Must Not a Nice to Have 21:06 The Jen Story and the Gasping Moment 22:17 How to Find Your First 10 to 15 Clients 28:38 The Personal Brand Play 33:06 Vision Is What AI Cannot Do 34:55 Hard for Computers Easy for Humans 36:13 Level 2 Making Your First Million With AI 37:18 The Replacement Ladder Framework 37:39 Admin First Then Delivery Then Marketing 39:09 Why Marketing Is the Biggest AI Category 39:32 Why You Should Keep Sales for Yourself 40:00 Level 5 Leadership and AI Agents 41:41 What a Fully AI Systems Business Looks Like 43:13 The Gym Owner With Three Locations 46:16 Shutting Down the Company for Two Days 46:37 Teaching the Whole Team to Code in Claude 49:28 Wayne the 62 Year Old Who Made $12K a Month 52:38 I Only Share What Actually Works 53:21 Whisper Flow and Talking to Your AI 56:41 Claude Chat Claude Coworker and Claude Code 57:57 The Claude Browser Extension 58:49 Claude Code Is Not Just for Developers 1:00:06 How to Migrate Your AI Memory Across Tools 1:01:08 Level 3 $1M to $10M and the Brand Play 1:02:05 Nobody Buys AI They Buy Trust 1:03:25 Brand Is Association and Association Is Trust 1:05:12 A Million Followers Is $10M in Activated Revenue 1:07:03 How to Keep AI From Becoming Slop 1:07:42 Human in the Loop 1:08:16 The 10 80 10 Rule and Why AI Is Now the 80 1:10:01 The Team FIRED Themselves 1:11:45 Dan's Free AI Curriculum for Your Team

Grant

167,714 views • 1 month ago

In the AI era, the next great software distribution company won’t look like an app store For the last decade-plus, building a strong software business was mostly a game of scarcity. The hard part was assembling the capital, taste, engineering, and distribution to build one enduring app. The discovery systems we built matched that world: app stores, SEO, search bars, rankings, reviews, ads, marketplaces AI has blown up these constraints Soon, anyone will be able to generate software for anything: a workout injury, a work project, a personal workflow, a one-off analysis, a weird niche need only they have, maybe only in a single moment Some apps will last forever, but most won’t. Many will exist for minutes or hours, and be created even faster But just because software can be created at the speed of thought doesn’t mean everyone will become a developer. Most people won’t want to prompt, build, debug, deploy, or manage software. They’ll just want to be matched with the right tool for the job in front of them The same technological wave enabling software creation at scale is also breaking software distribution at scale. Search assumes the best answer already exists somewhere. App stores assume software is something you browse, compare, install, and keep In a world of personal software, the real question becomes: Who understands enough about me, or has earned enough trust from me, to know what software should exist for me right now? The next great app distribution companies may look less like search engines and more like trusted relationships Some will win by importing and processing personal context: your goals, constraints, calendar, body, files, workflows, history, collaborators, and intent. Others will win by exporting taste and trust: experts, creators, communities, agents, and brands that people rely on to decide what is worth using Either way, the new gateway won’t be a search box or an app store shelf. It will be the layer that recommends, assembles, routes, and personalizes software at the moment of need This is the new frontier: context, recommendation, trust, and distribution in the age of infinite software If you’re building platforms or experiences for this future, we want to meet you. Apply to a16z speedrun 🧊. Applications for SR007 close this weekend Application link below
2:00

In the AI era, the next great software distribution company won’t look like an app store For the last decade-plus, building a strong software business was mostly a game of scarcity. The hard part was assembling the capital, taste, engineering, and distribution to build one enduring app. The discovery systems we built matched that world: app stores, SEO, search bars, rankings, reviews, ads, marketplaces AI has blown up these constraints Soon, anyone will be able to generate software for anything: a workout injury, a work project, a personal workflow, a one-off analysis, a weird niche need only they have, maybe only in a single moment Some apps will last forever, but most won’t. Many will exist for minutes or hours, and be created even faster But just because software can be created at the speed of thought doesn’t mean everyone will become a developer. Most people won’t want to prompt, build, debug, deploy, or manage software. They’ll just want to be matched with the right tool for the job in front of them The same technological wave enabling software creation at scale is also breaking software distribution at scale. Search assumes the best answer already exists somewhere. App stores assume software is something you browse, compare, install, and keep In a world of personal software, the real question becomes: Who understands enough about me, or has earned enough trust from me, to know what software should exist for me right now? The next great app distribution companies may look less like search engines and more like trusted relationships Some will win by importing and processing personal context: your goals, constraints, calendar, body, files, workflows, history, collaborators, and intent. Others will win by exporting taste and trust: experts, creators, communities, agents, and brands that people rely on to decide what is worth using Either way, the new gateway won’t be a search box or an app store shelf. It will be the layer that recommends, assembles, routes, and personalizes software at the moment of need This is the new frontier: context, recommendation, trust, and distribution in the age of infinite software If you’re building platforms or experiences for this future, we want to meet you. Apply to a16z speedrun 🧊. Applications for SR007 close this weekend Application link below

Josh Lu

11,092 views • 3 months ago

Here's my conversation all about FFmpeg, the legendary open-source software powering most video on the Internet. In the episode, I talk with Jean-Baptiste Kempf and Kieran Kunhya. JB is lead developer of VLC and Kieran is FFmpeg contributor, codec engineer, and the person behind the now-infamous FFmpeg account on X. VLC (VideoLAN), by the way, is also a legendary piece of open-source software: it's a video player that can open basically anything & has been downloaded over 6 billion times. I think both FFmpeg and VLC are two of the most important and impactful software systems ever created, both open source, and both created & maintained by volunteers: brilliant engineers from all walks of life. Thank you to everyone who contributed to FFmpeg and VLC, and in general to all engineers giving their heart & soul to building systems used by millions (or billions) of people, and often doing so not for money, status, or fame, but purely for the love of building great software and doing good for the world. Thank you to the builders! 🙏❤️ Shoutouts in this chat to John Carmack Andrej Karpathy Elon Musk Tim Sweeney and everyone who is a contributor & fan of open source! It's here on X in full and is up everywhere else (see comment). Timestamps: 0:00 - Episode highlight 2:17 - Introduction 5:35 - Weirdest things VLC opens 9:59 - How video playback works 19:20 - Video codecs and containers 30:07 - FFmpeg explained 51:07 - Linus Torvalds 55:46 - Turning down millions to keep VLC ad-free 1:10:04 - FFmpeg & Google drama 1:29:18 - FFmpeg developers 1:35:55 - VLC and FFmpeg 1:40:29 - History of FFmpeg 1:43:46 - Reverse engineering codecs 1:57:01 - FFmpeg testing 2:01:08 - Assembly code (handwritten) 2:25:26 - Rust programming language 2:34:42 - FFmpeg and Libav fork 2:43:04 - Open source burnout 2:50:51 - x264 and internet video 3:04:07 - Video compression basics 3:11:04 - CIA and fake VLC 3:21:39 - Ultra low latency streaming 3:39:07 - AV2 codec and video patents 3:48:59 - VLC backdoors 3:59:14 - Video archiving 4:05:51 - Future of FFmpeg and VLC
4:18:21

Here's my conversation all about FFmpeg, the legendary open-source software powering most video on the Internet. In the episode, I talk with Jean-Baptiste Kempf and Kieran Kunhya. JB is lead developer of VLC and Kieran is FFmpeg contributor, codec engineer, and the person behind the now-infamous FFmpeg account on X. VLC (VideoLAN), by the way, is also a legendary piece of open-source software: it's a video player that can open basically anything & has been downloaded over 6 billion times. I think both FFmpeg and VLC are two of the most important and impactful software systems ever created, both open source, and both created & maintained by volunteers: brilliant engineers from all walks of life. Thank you to everyone who contributed to FFmpeg and VLC, and in general to all engineers giving their heart & soul to building systems used by millions (or billions) of people, and often doing so not for money, status, or fame, but purely for the love of building great software and doing good for the world. Thank you to the builders! 🙏❤️ Shoutouts in this chat to John Carmack Andrej Karpathy Elon Musk Tim Sweeney and everyone who is a contributor & fan of open source! It's here on X in full and is up everywhere else (see comment). Timestamps: 0:00 - Episode highlight 2:17 - Introduction 5:35 - Weirdest things VLC opens 9:59 - How video playback works 19:20 - Video codecs and containers 30:07 - FFmpeg explained 51:07 - Linus Torvalds 55:46 - Turning down millions to keep VLC ad-free 1:10:04 - FFmpeg & Google drama 1:29:18 - FFmpeg developers 1:35:55 - VLC and FFmpeg 1:40:29 - History of FFmpeg 1:43:46 - Reverse engineering codecs 1:57:01 - FFmpeg testing 2:01:08 - Assembly code (handwritten) 2:25:26 - Rust programming language 2:34:42 - FFmpeg and Libav fork 2:43:04 - Open source burnout 2:50:51 - x264 and internet video 3:04:07 - Video compression basics 3:11:04 - CIA and fake VLC 3:21:39 - Ultra low latency streaming 3:39:07 - AV2 codec and video patents 3:48:59 - VLC backdoors 3:59:14 - Video archiving 4:05:51 - Future of FFmpeg and VLC

Lex Fridman

511,891 views • 3 months ago

SaaS isn’t dead, it just needs to become agent-native. Linear (Linear) is a great example of how: They pivoted the product to be used by both humans and agents, and that has made them one of the premier software tools in the agent-native era. I had Linear’s cofounder and CEO Karri Saarinen on Every 📧's AI & I to talk about how a product management tool for human software developers became an agent-native tool—and how Linear’s trajectory reveals a bright future for SaaS businesses: - Speed means decisions matter more, not less. AI makes it easy to have an idea and build it without considering whether its existence is justified. When ChatGPT was released, SaaS companies were launching their own chatbots left, right, and center. Instead of jumping on the bandwagon, Linear stopped to consider whether the application was useful. (It wasn’t.) - Just because the technology has changed doesn’t mean your mission should. Karri attributes Linear’s success to never losing sight of what matters: helping teams develop great software. Instead of chasing trends, Linear focused on understanding how AI was impacting its customers’ workflows—and updating its product accordingly. - Agents are now first-class users. Linear never tried to change what it was or did well; it just expanded the user base. Companies can now kick off agents inside Linear, manage them, and track what they're working on alongside the humans on the team, which explains why Codex, Coinbase, and Brex all run their agents on Linear. This is a must watch for anyone interested in how an agent-native SaaS company operates. Watch below! Timestamps: Introduction and how Every first discovered Linear: 00:00:39 Why Linear waited to ship AI features instead of rushing to chatbots: 00:02:00 Linear's agent platform and becoming the system that guides AI agents: 00:05:06 Why "SaaS is dead" is a simplistic narrative: 00:07:42 How Linear adopted AI coding tools internally: 00:12:18 AI's impact on product building workflows—speed versus thoughtfulness: 00:17:45 The value of conceptual work and thinking before shipping: 00:22:18 How AI is reshaping Linear's product strategy: 00:29:30 Demo: Linear's agent skills, shared context, and code review workflow: 00:37:18 The future of product development and the enduring role of human judgment: 00:47:48
52:48

SaaS isn’t dead, it just needs to become agent-native. Linear (Linear) is a great example of how: They pivoted the product to be used by both humans and agents, and that has made them one of the premier software tools in the agent-native era. I had Linear’s cofounder and CEO Karri Saarinen on Every 📧's AI & I to talk about how a product management tool for human software developers became an agent-native tool—and how Linear’s trajectory reveals a bright future for SaaS businesses: - Speed means decisions matter more, not less. AI makes it easy to have an idea and build it without considering whether its existence is justified. When ChatGPT was released, SaaS companies were launching their own chatbots left, right, and center. Instead of jumping on the bandwagon, Linear stopped to consider whether the application was useful. (It wasn’t.) - Just because the technology has changed doesn’t mean your mission should. Karri attributes Linear’s success to never losing sight of what matters: helping teams develop great software. Instead of chasing trends, Linear focused on understanding how AI was impacting its customers’ workflows—and updating its product accordingly. - Agents are now first-class users. Linear never tried to change what it was or did well; it just expanded the user base. Companies can now kick off agents inside Linear, manage them, and track what they're working on alongside the humans on the team, which explains why Codex, Coinbase, and Brex all run their agents on Linear. This is a must watch for anyone interested in how an agent-native SaaS company operates. Watch below! Timestamps: Introduction and how Every first discovered Linear: 00:00:39 Why Linear waited to ship AI features instead of rushing to chatbots: 00:02:00 Linear's agent platform and becoming the system that guides AI agents: 00:05:06 Why "SaaS is dead" is a simplistic narrative: 00:07:42 How Linear adopted AI coding tools internally: 00:12:18 AI's impact on product building workflows—speed versus thoughtfulness: 00:17:45 The value of conceptual work and thinking before shipping: 00:22:18 How AI is reshaping Linear's product strategy: 00:29:30 Demo: Linear's agent skills, shared context, and code review workflow: 00:37:18 The future of product development and the enduring role of human judgment: 00:47:48

Dan Shipper 📧

36,359 views • 4 months ago

Many AI apps today feel like the "horseless carriages" of the late 19th century, which "swapped a horse for an engine without redesigning the vehicle to handle higher speeds." They pack powerful tech into outdated interfaces. YC's Pete Koomen (Pete Koomen) thinks we can do better. He joined Tom Blomfield and David Lieb to lay out a new vision for how AI should actually work: not as a chatbot bolted onto legacy software, but as a customizable tool that helps people offload the work they don't want to do. From editable system prompts to agents that act more like collaborators, they break down what it means to build AI-native software—and why the future belongs to products that let users teach machines how they think. 0:00 – Intro 0:52 – Why AI apps are broken 2:39 – How Gmail’s AI features fall short 4:00 – A better way to build AI apps 5:27 – The hidden system prompt 7:57 – What if you could access the system prompt? 9:40 – The developer-user divide in software 10:48 – The "horseless carriage" metaphor 13:35 – Email reading agent demo 14:34 – Everyone can be a prompt engineer 16:23 – Why coding agents feel magical 21:42 – Training AI like a human assistant 28:45 – The problem with chatbot interfaces 29:10 – Advice for founders
30:07

Many AI apps today feel like the "horseless carriages" of the late 19th century, which "swapped a horse for an engine without redesigning the vehicle to handle higher speeds." They pack powerful tech into outdated interfaces. YC's Pete Koomen (Pete Koomen) thinks we can do better. He joined Tom Blomfield and David Lieb to lay out a new vision for how AI should actually work: not as a chatbot bolted onto legacy software, but as a customizable tool that helps people offload the work they don't want to do. From editable system prompts to agents that act more like collaborators, they break down what it means to build AI-native software—and why the future belongs to products that let users teach machines how they think. 0:00 – Intro 0:52 – Why AI apps are broken 2:39 – How Gmail’s AI features fall short 4:00 – A better way to build AI apps 5:27 – The hidden system prompt 7:57 – What if you could access the system prompt? 9:40 – The developer-user divide in software 10:48 – The "horseless carriage" metaphor 13:35 – Email reading agent demo 14:34 – Everyone can be a prompt engineer 16:23 – Why coding agents feel magical 21:42 – Training AI like a human assistant 28:45 – The problem with chatbot interfaces 29:10 – Advice for founders

Y Combinator

304,853 views • 1 year ago

Tomorrow Apple will announce the new Siri, finally. I used to be more excited by what Apple was about to launch. I get more excited now by enterpreneurs who are trying to bring us better tools. Particularly in developer tools, which is incredibly crowded, with 1,800 companies alone: While we'll all use the new Siri to find a place to eat nearby, or figure out where we parked our car, I seriously doubt anyone will use it to build new AI infrastructure at their businesses, or switch from coding with OpenAI or Anthropic to using it. At best it might set that up for future work. Google's model underneath thew new Siri will bring new multi-modality features that will be needed. But I don't expect it to take the energy away from people like Prasanna Sankar, Prasanna S, who I interview here about his new "smartest software engineer" system: This video is a deep dive into the next generation of AI-powered software development, centered on a conversation with Prasanna, founder of Vorflux and previously a founder of Rippling. The discussion explains why AI coding tools are moving beyond simple “vibe coding” and autocomplete toward more powerful cloud-based agent systems that can plan, build, test, review, and ship software with far less human micromanagement. I learned long ago to watch the developers for the real innovation. That said, sure hope Apple pulls something out that excites us, I just don't expect it. Do you? You will learn more about the future of software development by watching this, I expect, than WWDC tomorrow. But I'll be watching hoping I'm wrong.
58:41

Tomorrow Apple will announce the new Siri, finally. I used to be more excited by what Apple was about to launch. I get more excited now by enterpreneurs who are trying to bring us better tools. Particularly in developer tools, which is incredibly crowded, with 1,800 companies alone: While we'll all use the new Siri to find a place to eat nearby, or figure out where we parked our car, I seriously doubt anyone will use it to build new AI infrastructure at their businesses, or switch from coding with OpenAI or Anthropic to using it. At best it might set that up for future work. Google's model underneath thew new Siri will bring new multi-modality features that will be needed. But I don't expect it to take the energy away from people like Prasanna Sankar, Prasanna S, who I interview here about his new "smartest software engineer" system: This video is a deep dive into the next generation of AI-powered software development, centered on a conversation with Prasanna, founder of Vorflux and previously a founder of Rippling. The discussion explains why AI coding tools are moving beyond simple “vibe coding” and autocomplete toward more powerful cloud-based agent systems that can plan, build, test, review, and ship software with far less human micromanagement. I learned long ago to watch the developers for the real innovation. That said, sure hope Apple pulls something out that excites us, I just don't expect it. Do you? You will learn more about the future of software development by watching this, I expect, than WWDC tomorrow. But I'll be watching hoping I'm wrong.

Robert Scoble

37,960 views • 2 months ago

Knowing how LLM contexts work and how to work around context limitations – aka “context engineering” – is becoming so important. No better person to explain than dex Timestamps: 00:00 Intro 01:33 Dex’s path into tech 03:34 Early work in platform engineering 05:28 Replicated 11:24 Metalytics 12:36 12-factor agents 18:27 Context engineering 23:38 Harness engineering 26:11 Context overload 30:45 Loop engineering 44:34 Software factories before and after AI 50:33 Automation limits 55:18 Three options for automating 59:00 RPI framework 1:04:16 Intentional compaction 1:11:48 Token harder vs. token smarter 1:16:44 AI slop 1:19:15 HumanLayer 1:29:09 Book recommendation Brought to you by: • Antithesis — with Antithesis, you can use AI agents to work on critical systems without worrying about correctness. Teams like Jane Street, and the etcd community use Antithesis to ship better code, faster. • Buildkite — the CI orchestration platform built for reliable scale. Used by OpenAI, Anthropic, Cursor, Meta, Uber, Ramp, Nvidia, Airbnb and many more. • Sentry — application monitoring software built by developers, for developers. Check out their AI agent, Seer AI, and Sentry MCP. Three interesting learnings from this episode: 1. Lesson learned: Shipping unread code spells disaster within months. Dex experimented with having the model write the code and humans not reviewing anything in July 2025. Four months later, they shut things down and threw the whole system out. Production broke, and no matter how much the team prompted Opus 4.1, the model could not find the root cause. Once fixed, it took three weeks (!!) to re-onboard to a codebase no human had ever read 2. Context engineering 101: figure out where the “dumb zone” begins. As a rule of thumb, the less of the context window that is used, the better the outcomes are. This is because the attention mechanism is quadratic: the more that goes into the context window, the more compute is required to process it all. 3. “You’re completely right!” or “you’re right to push back on that” are phrases that mean it’s time to start a new session. These responses mean the LLM session is trajectory-poisoned, and you’re wasting time and tokens to continue. This is because models are autoregressive.
1:33:10

Knowing how LLM contexts work and how to work around context limitations – aka “context engineering” – is becoming so important. No better person to explain than dex Timestamps: 00:00 Intro 01:33 Dex’s path into tech 03:34 Early work in platform engineering 05:28 Replicated 11:24 Metalytics 12:36 12-factor agents 18:27 Context engineering 23:38 Harness engineering 26:11 Context overload 30:45 Loop engineering 44:34 Software factories before and after AI 50:33 Automation limits 55:18 Three options for automating 59:00 RPI framework 1:04:16 Intentional compaction 1:11:48 Token harder vs. token smarter 1:16:44 AI slop 1:19:15 HumanLayer 1:29:09 Book recommendation Brought to you by: • Antithesis — with Antithesis, you can use AI agents to work on critical systems without worrying about correctness. Teams like Jane Street, and the etcd community use Antithesis to ship better code, faster. • Buildkite — the CI orchestration platform built for reliable scale. Used by OpenAI, Anthropic, Cursor, Meta, Uber, Ramp, Nvidia, Airbnb and many more. • Sentry — application monitoring software built by developers, for developers. Check out their AI agent, Seer AI, and Sentry MCP. Three interesting learnings from this episode: 1. Lesson learned: Shipping unread code spells disaster within months. Dex experimented with having the model write the code and humans not reviewing anything in July 2025. Four months later, they shut things down and threw the whole system out. Production broke, and no matter how much the team prompted Opus 4.1, the model could not find the root cause. Once fixed, it took three weeks (!!) to re-onboard to a codebase no human had ever read 2. Context engineering 101: figure out where the “dumb zone” begins. As a rule of thumb, the less of the context window that is used, the better the outcomes are. This is because the attention mechanism is quadratic: the more that goes into the context window, the more compute is required to process it all. 3. “You’re completely right!” or “you’re right to push back on that” are phrases that mean it’s time to start a new session. These responses mean the LLM session is trajectory-poisoned, and you’re wasting time and tokens to continue. This is because models are autoregressive.

Gergely Orosz

63,174 views • 1 month ago