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.

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... show more

Ben Awad

128,097 subscribers

535,954 views • 10 months ago •via X (Twitter)

Education Science & Technology

Anya Rossi• Live Now

Private livecam show

33 Comments

Khalid on Crypto10 months ago

"Use AI to help you define specs" and "Have AI navigate your browser" are the worst advice to give to anyone who wants to develop their skills in tech. Don't delegate the design and architecture choices and priorities to the LLM. Remember, these models are trained on a lot of slop data... so it will more likely output slop unless you guide it with the design patterns and the anti-patterns. You 100% need to read over the code changes to make sure it doesn't over abstract or worse use complex solutions to simple problems! But yes, AI is really good for writing functional requirement test cases.

bayge.meow (Alex)10 months ago

AI programs your code, AI defines the scope, AI fucks your wife too? No thanks!

shayu10 months ago

The slop has depressed you out of your mind dawg

f1shy-dev10 months ago

omg new development content from benawad after like 6 years

Joseph Hurtado - Founder Granata Consulting10 months ago

You are going to quickly become a useless developer this way. Horrible advice. Use AI, don’t become it’s ignorant manager.

Ahmad10 months ago

The below is critically important to prevent Agents from leaving you with a messy codebase BTW

Aiden Bai10 months ago

he's back

Adi | Resolved Markets10 months ago

feels right until prod screams

Adetunji | Software Engineer (Web & Mobile)10 months ago

My take is this is really bad advice The more you give AI to do your work the more your mental capacity to handle complex tasks reduce Yeah you should give AI repeatable tasks like creating modals you have done before But giving it everything to do doesn’t teach you anything if that is what you are going for If you want to get an idea out there for users to test out quickly then spam AI but there should be a limit

Don10 months ago

I totally agree. We are all pretty much PMs.

Dan Camacho10 months ago

Might want to take a gander if you're a developer in 2026... hope this helps

trainface10 months ago

model arbitrage

Simple Jack10 months ago

Fucking idiot

Neky Tasnim10 months ago

I keep seeing this kind of advice and the current tech space feels so incredibly elitist for fresh grads without jobs, because these tools are literally expensive, and apparently using these tools is a must-have skill now. AI has turned coding into capitalism.

camjo10 months ago

i hate the fact we have to keep switching to get the best of the best

taheer10 months ago

But would DSA still matter ? IMHO YES, because it changes the way you think about problems would love to know your take on this ?

Oren10 months ago

AI is not at the level yet that it can build a production level complex system, you still need to be the main architect and thinker. he can do the rest.

- Elijah Muraoka -10 months ago

well stated ben awad

The Chin Man10 months ago

I don't trust it enough yet to merely "skim" code changes, I still read every line of every PR. Time-consuming, but I've caught a couple issues that could have been pretty bad if they reached prod. This has gotten a lot better over time though.

Zoltán Szőgyényi10 months ago

the list is basically ai for everything mate

Graham Fleming10 months ago

I make a lot of mistakes So AI teaches me a lot

Rituraj9 months ago

We aren't writers anymore; we are Managing Editors of a very prolific, very fast, but occasionally hallucinating intern. The skill set has shifted entirely from "How do I implement this algorithm?" to "Does this implementation actually meet the spec?" The bottleneck is no longer typing speed; it's reading comprehension.

Just a frog10 months ago

I'm going to keep writing my own code, that way I'll keep getting better at it and I'll continue to be capable of maintaining my work. While you all atrophy your brains, I'll keep on actually being able to do my work.

Galilean Liberal ✡️🌍🇮🇱🇺🇦🇹🇼🇺🇸🍦10 months ago

- stop listening to Ben awad

Seven Liu10 months ago

taste is the only moat left. if everyone can ship a feature, the winner is whoever knows what to delete.

vic || -victor.eth10 months ago

I wish there was an OSS solution, but @warpdotdev is doing it best

Thaddeus10 months ago

AI slop will be the biggest challenge of 2026

Yogesh Gupta9 months ago

Gud luck after 1 month, My advice to newdevs, off autosuggestion, they are skill killers.

Saïd Aitmbarek10 months ago

~95% of klocs vibe coded so far

bibhuti10 months ago

what about writing code like a human

Jesse9 months ago

well said

square 🟥10 months ago

Omg I remember seeing u on TikTok a while back.. cool that ur on here

Neer10 months ago

2026: software engineers become AI project managers

Related Videos

I'm giving away Claude Code for FREE. Yes, you read that right -- the world's best AI, now completely FREE. My mission is to get the next billion people to write great software. I believe EVERYONE should have access to the best AI, but so many are constrained by costs. I'm solving this by: disrupting the world's fastest growing industry = AI + with the most proven business model = Ads You can actually try it out now -- just one line of code, and you unlock all the powers of Claude Code, for free. how it works: 1. sign up on Giga AI Free 2. change Claude Code env variables to use our inference endpoint 2. to support the free usage, we'll add ads inside the AI responses (only contextual and relevant ads, no spam) Since we get too many signups, there's a waitlist, but we'll be rolling it out to the maximum people as we can. Watch the video to get started & comment and retweet to get access first.

I'm giving away Claude Code for FREE. Yes, you read that right -- the world's best AI, now completely FREE. My mission is to get the next billion people to write great software. I believe EVERYONE should have access to the best AI, but so many are constrained by costs. I'm solving this by: disrupting the world's fastest growing industry = AI + with the most proven business model = Ads You can actually try it out now -- just one line of code, and you unlock all the powers of Claude Code, for free. how it works: 1. sign up on Giga AI Free 2. change Claude Code env variables to use our inference endpoint 2. to support the free usage, we'll add ads inside the AI responses (only contextual and relevant ads, no spam) Since we get too many signups, there's a waitlist, but we'll be rolling it out to the maximum people as we can. Watch the video to get started & comment and retweet to get access first.

Namanyay

489,200 views • 1 year ago

Mark Zuckerberg: AI engineers will eventually build most of the code at Meta, instead of human engineers. “We’re gonna have an AI that can effectively be a mid-level engineer at your company.” “It can write code.” “Over time, we’ll get to the point where a lot of the code in our apps is actually gonna be built by AI engineers.” “Even the AI that we generate will be built by AI engineers instead of people engineers.”

Mark Zuckerberg: AI engineers will eventually build most of the code at Meta, instead of human engineers. “We’re gonna have an AI that can effectively be a mid-level engineer at your company.” “It can write code.” “Over time, we’ll get to the point where a lot of the code in our apps is actually gonna be built by AI engineers.” “Even the AI that we generate will be built by AI engineers instead of people engineers.”

Veee

145,412 views • 10 days 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

296,928 views • 1 year ago

Ignore AI. If you want to prepare for the future don't learn to code. Don't try to master AI. Read books. Doesn't matter which ones. Just read. Because reading teaches you to think for yourself. To have a dialogue inside your own head. That is the only skill that will matter. And it's the one thing AI cannot give you.

Ignore AI. If you want to prepare for the future don't learn to code. Don't try to master AI. Read books. Doesn't matter which ones. Just read. Because reading teaches you to think for yourself. To have a dialogue inside your own head. That is the only skill that will matter. And it's the one thing AI cannot give you.

Predictive History

25,963 views • 4 months ago

VS Code is adding new AI features every day to help you write code faster and better than ever. Here are a few favorites that I have that you should go try out right now. #vscode #githubcopilot

VS Code is adding new AI features every day to help you write code faster and better than ever. Here are a few favorites that I have that you should go try out right now. #vscode #githubcopilot

James Montemagno

24,786 views • 1 year ago

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

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

Santiago

64,477 views • 10 months ago

“100% OF MY CODE IS WRITTEN BY CLADE CODE” so I guess the lesson is, if you’re building 100% of an app with AI you should at least build solid harnesses around it to avoid production disasters. I don’t want to be the guy who kicks someone down when a mistake happens, but this is becoming a PATTERN. we saw the same thing happen to Amazon when Kiro deleted a production environment and caused a 13-hour outage. assuming the Claude Code team similar to Boris has relied 100% on Claude to build itself, there seems to be a lesson here to learn, earned through blood and tears: YOU SHOULD MAKE AS MUCH EFFORT TO BUILD AGAINST AI IF YOU BUILD WITH AI.

“100% OF MY CODE IS WRITTEN BY CLADE CODE” so I guess the lesson is, if you’re building 100% of an app with AI you should at least build solid harnesses around it to avoid production disasters. I don’t want to be the guy who kicks someone down when a mistake happens, but this is becoming a PATTERN. we saw the same thing happen to Amazon when Kiro deleted a production environment and caused a 13-hour outage. assuming the Claude Code team similar to Boris has relied 100% on Claude to build itself, there seems to be a lesson here to learn, earned through blood and tears: YOU SHOULD MAKE AS MUCH EFFORT TO BUILD AGAINST AI IF YOU BUILD WITH AI.

ℏεsam

19,347 views • 7 months ago

"The one thing that's going to be truly future proof is judgment. What is the biggest challenge when you have a thousand AI engineers writing code? AI slop. In an era when you can do everything, the question is which of these things matter. On the engineer side, it is evaluating the code. Which of this code is even valuable? You can have AI engineers writing beautiful code that could be wrong, that could have bugs in it, that could be vulnerable. Someone needs to review it. Make sure to have a human review at some point, especially critical code that is in the core of your system. On the product side is judgment around what needs to be built and evaluating. And similarly in design, you have to have judgment around, does it make sense in the broader design system. I think this judgment is the number one thing that humans are going to bring in an era of infinite productivity."

"The one thing that's going to be truly future proof is judgment. What is the biggest challenge when you have a thousand AI engineers writing code? AI slop. In an era when you can do everything, the question is which of these things matter. On the engineer side, it is evaluating the code. Which of this code is even valuable? You can have AI engineers writing beautiful code that could be wrong, that could have bugs in it, that could be vulnerable. Someone needs to review it. Make sure to have a human review at some point, especially critical code that is in the core of your system. On the product side is judgment around what needs to be built and evaluating. And similarly in design, you have to have judgment around, does it make sense in the broader design system. I think this judgment is the number one thing that humans are going to bring in an era of infinite productivity."

Patrick OShaughnessy

24,818 views • 9 months ago

How to hide the claude code sidebar in cursor without exiting it! now you can use the claude code extension in cursor and toggle it off when you need some space to code without an AI agent 😱

How to hide the claude code sidebar in cursor without exiting it! now you can use the claude code extension in cursor and toggle it off when you need some space to code without an AI agent 😱

Ian Nuttall

22,322 views • 1 year ago

this is the CLEAREST explanation of "ralph wiggum" on the internet and how you can use it with claude code/amp/etc and have AI agents build software for you 24/7 even while you sleep

this is the CLEAREST explanation of "ralph wiggum" on the internet and how you can use it with claude code/amp/etc and have AI agents build software for you 24/7 even while you sleep

GREG ISENBERG

304,384 views • 9 months ago

Do you understand what's happening? It's not just "AI can make iOS apps" anymore. AI is eating up the entire software industry. Even Dario Amodei (founder of Claude) said 90% of all code in the world would be written by AI. In 20 minutes, I built this Duolingo for AI upskilling app with Superapp. The idea was simple - almost everyone today knows AI is the future, but most of them are still feeling left out. Their current jobs don't leave them with enough time to actually learn and build stuff with AI. There's AI dev, video making, animations, testing, etc. But no time or clear direction. So I built an app to fix exactly this. With AgentIQ, you get new lessons every day. Every time you learn something, it gets added to your skillset and automatically refreshes your portfolio. You level up with every new chapter/pathway. It is self-paced but gamified enough (like Duolingo) that you never get out of touch. Without spending hours or tonnes of money, you build stuff with n8n, openclaw, etc. You ship AI videos to market your own AI apps. This could be a proper ed-tech company if someone wants to continue building on top. Happy to share the entire source code with you if you wanna pursue it. Like + comment "AGENT" and I'll send you the app link, a comprehensive guide to build production-ready apps, and the entire source code for this.

Do you understand what's happening? It's not just "AI can make iOS apps" anymore. AI is eating up the entire software industry. Even Dario Amodei (founder of Claude) said 90% of all code in the world would be written by AI. In 20 minutes, I built this Duolingo for AI upskilling app with Superapp. The idea was simple - almost everyone today knows AI is the future, but most of them are still feeling left out. Their current jobs don't leave them with enough time to actually learn and build stuff with AI. There's AI dev, video making, animations, testing, etc. But no time or clear direction. So I built an app to fix exactly this. With AgentIQ, you get new lessons every day. Every time you learn something, it gets added to your skillset and automatically refreshes your portfolio. You level up with every new chapter/pathway. It is self-paced but gamified enough (like Duolingo) that you never get out of touch. Without spending hours or tonnes of money, you build stuff with n8n, openclaw, etc. You ship AI videos to market your own AI apps. This could be a proper ed-tech company if someone wants to continue building on top. Happy to share the entire source code with you if you wanna pursue it. Like + comment "AGENT" and I'll send you the app link, a comprehensive guide to build production-ready apps, and the entire source code for this.

Kritarth Mittal | Soshals

25,560 views • 6 months ago

THIS IS WHAT AI PENTESTING SHOULD LOOK LIKE IN 2026 Someone built Shannon, an open source AI pentesting tool that doesn’t just scan your app from the outside. It reads the source code. Then it uses AI to map potential attack paths, identify vulnerabilities, and test the application before you ship it. The workflow is basically: → point Shannon at your code → connect your Claude API → let it analyze the application → get the findings in a dashboard Instead of waiting for a security team to manually hunt through every part of your codebase, you can have an AI security researcher working through it automatically. And because it’s white-box, it can see things traditional scanners can’t. This is where AI + cybersecurity gets REALLY interesting. Just use it on systems you own or have explicit permission to test. REPO BELOW

THIS IS WHAT AI PENTESTING SHOULD LOOK LIKE IN 2026 Someone built Shannon, an open source AI pentesting tool that doesn’t just scan your app from the outside. It reads the source code. Then it uses AI to map potential attack paths, identify vulnerabilities, and test the application before you ship it. The workflow is basically: → point Shannon at your code → connect your Claude API → let it analyze the application → get the findings in a dashboard Instead of waiting for a security team to manually hunt through every part of your codebase, you can have an AI security researcher working through it automatically. And because it’s white-box, it can see things traditional scanners can’t. This is where AI + cybersecurity gets REALLY interesting. Just use it on systems you own or have explicit permission to test. REPO BELOW

MAX

13,311 views • 1 month ago

An MCP server that detects production-grade code quality issues in real-time! Even though AI is now generating code at light speed, the engineering bottleneck has just moved from writing to reviewing, and now devs spend 90% of their debugging time on AI-generated code. AI reviewers aren't that reliable either because they share the same fundamental blind spots as AI generators do: - They pattern match, not proof check. - They validate syntax, not system behavior. - They review code, not consequences. I have been using the SonarQube MCP Server (by Sonar) to solve this. It produces enterprise-grade code analysis and returns instant feedback on bugs, vulnerabilities, and code smells right where you're working (Claude Code, Cursor, etc.). Its capabilities have emerged from the 750B+ lines of code SonarQube processes daily, so it has seen every bug pattern that exists. This includes: - Security vulnerabilities (SQL injection, XSS, hardcoded secrets) - Code smells and technical debt - Test coverage gaps - Maintainability issues The setup is simple: - Install the SonarQube MCP server - Add it to your AI assistant's config Done! SonarQube is now part of your AI coding workflow. I have shared the GitHub repo in the replies! P.S. Thanks to Sonar for working with me today.

An MCP server that detects production-grade code quality issues in real-time! Even though AI is now generating code at light speed, the engineering bottleneck has just moved from writing to reviewing, and now devs spend 90% of their debugging time on AI-generated code. AI reviewers aren't that reliable either because they share the same fundamental blind spots as AI generators do: - They pattern match, not proof check. - They validate syntax, not system behavior. - They review code, not consequences. I have been using the SonarQube MCP Server (by Sonar) to solve this. It produces enterprise-grade code analysis and returns instant feedback on bugs, vulnerabilities, and code smells right where you're working (Claude Code, Cursor, etc.). Its capabilities have emerged from the 750B+ lines of code SonarQube processes daily, so it has seen every bug pattern that exists. This includes: - Security vulnerabilities (SQL injection, XSS, hardcoded secrets) - Code smells and technical debt - Test coverage gaps - Maintainability issues The setup is simple: - Install the SonarQube MCP server - Add it to your AI assistant's config Done! SonarQube is now part of your AI coding workflow. I have shared the GitHub repo in the replies! P.S. Thanks to Sonar for working with me today.

Avi Chawla

28,628 views • 10 months ago

You probably don’t use just one AI agent anymore. Maybe Codex for coding. Claude Code for research. Cursor for quick edits. Hermes for the rest. Each one is great at something different. But every time you switch, you have to start over — re-explaining your project, preferences, and the way you like to work. Your agents know how to help you. They just don’t share a memory of you. memU just shipped an update that fixes this. One personal memory, shared across every agent and device you use. What Codex learned last night, Claude Code can remember this morning. 🧵

You probably don’t use just one AI agent anymore. Maybe Codex for coding. Claude Code for research. Cursor for quick edits. Hermes for the rest. Each one is great at something different. But every time you switch, you have to start over — re-explaining your project, preferences, and the way you like to work. Your agents know how to help you. They just don’t share a memory of you. memU just shipped an update that fixes this. One personal memory, shared across every agent and device you use. What Codex learned last night, Claude Code can remember this morning. 🧵

Hasan

50,678 views • 3 months ago

AI is changing the software engineering craft. Anders Hejlsberg (Anders Hejlsberg) - creator of C#, TypeScript and industry legend - on why code review needs to get more enjoyable in response: #1 - AI is shifting the craft from writing code, to reviewing code: "In a sense, we're all turning into project managers. We can have an army of junior programmers, called agents, that will just spit out reams of code but someone's got to have the big picture and review all of that. And so, increasingly, our craft is going from one of writing the code, to one of reviewing the code and building the architecture of the code and overseeing the work. It's a different kind of craft. It's a different kind of enjoyment. I've always liked writing the code. To me that was the fulfilling part, seeing it work. In a way, AI robs a little bit of that, because I am less interested in reviewing code." #2 - The code review experience should be improved: "I think we could also make the process of reviewing code much more interesting than it is today. I mean, today, you see a list of diffs in alphabetical order and now it's up to you to make heads or tails of it. There are more pedagogical ways of presenting that. And you could have commentary generated by the AI that tells you what the changes are and whatever, and then tries to guide you along. So that symbiotic relationship, I think we need to work on that more and to keep the enjoyment in there."

AI is changing the software engineering craft. Anders Hejlsberg (Anders Hejlsberg) - creator of C#, TypeScript and industry legend - on why code review needs to get more enjoyable in response: #1 - AI is shifting the craft from writing code, to reviewing code: "In a sense, we're all turning into project managers. We can have an army of junior programmers, called agents, that will just spit out reams of code but someone's got to have the big picture and review all of that. And so, increasingly, our craft is going from one of writing the code, to one of reviewing the code and building the architecture of the code and overseeing the work. It's a different kind of craft. It's a different kind of enjoyment. I've always liked writing the code. To me that was the fulfilling part, seeing it work. In a way, AI robs a little bit of that, because I am less interested in reviewing code." #2 - The code review experience should be improved: "I think we could also make the process of reviewing code much more interesting than it is today. I mean, today, you see a list of diffs in alphabetical order and now it's up to you to make heads or tails of it. There are more pedagogical ways of presenting that. And you could have commentary generated by the AI that tells you what the changes are and whatever, and then tries to guide you along. So that symbiotic relationship, I think we need to work on that more and to keep the enjoyment in there."

The Pragmatic Engineer

39,073 views • 5 months ago

Head of Engineering Shopify: "AI writes the code, AI reviews the code. Your job is just to write the loops around it." 26 minutes on how AI changed the way 3,000 engineers work inside a single company. Ignoring it while everyone else uses AI to do more is the fastest way to fall behind. Watch it, then read the step by step guide on loops below.

Head of Engineering Shopify: "AI writes the code, AI reviews the code. Your job is just to write the loops around it." 26 minutes on how AI changed the way 3,000 engineers work inside a single company. Ignoring it while everyone else uses AI to do more is the fastest way to fall behind. Watch it, then read the step by step guide on loops below.

Anatoli Kopadze

718,321 views • 4 months ago

This is how the Intercom design team uses AI to prototype directly in code Designers using AI tools should copy this AI workflow to ship faster 👀 Watch the full video on Sneak Peek: Domingo Widen shows how Intercom design team uses Figma Code Connect + Claude to design directly in code 👇

This is how the Intercom design team uses AI to prototype directly in code Designers using AI tools should copy this AI workflow to ship faster 👀 Watch the full video on Sneak Peek: Domingo Widen shows how Intercom design team uses Figma Code Connect + Claude to design directly in code 👇

Jayneil Dalal

54,117 views • 8 months ago