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.

Code quality, taste and judgment matter - especially now that agents write most of the first draft. Sonar helps set your quality gate:

Addy Osmani

409,093 subscribers

584,837 views • 26 days ago •via X (Twitter)

Science & Technology Education News & Politics

Anya Rossi• Live Now

Private livecam show

0 Comments

No comments available

Comments from the original post will appear here

Related Videos

Code quality, taste and judgement matter. Sonar is great for catching bug and security issues on every commit. Here's why I like using it. Learn more:

Code quality, taste and judgement matter. Sonar is great for catching bug and security issues on every commit. Here's why I like using it. Learn more:

Addy Osmani

801,576 views • 1 month ago

The quality of your AI outputs = the quality of the context you feed it. Here’s the easiest upgrade most people miss: Connect your Obsidian vault to your AI agents. Now your agents can: read your research understand your business track your goals spot content gaps write assets from your own notes No APIs. No setup headaches. Just local markdown files powering smarter agents.

The quality of your AI outputs = the quality of the context you feed it. Here’s the easiest upgrade most people miss: Connect your Obsidian vault to your AI agents. Now your agents can: read your research understand your business track your goals spot content gaps write assets from your own notes No APIs. No setup headaches. Just local markdown files powering smarter agents.

Julian Goldie SEO

18,054 views • 5 months ago

Introducing the Matter CLI. Now your agents can access Matter on your behalf. > Write me a digest of this week’s news from my inbox. > Find articles about Iran and add ‘iran’ tag. > Pull all my highlights about parenthood. Try it in Claude Code, Codex, or wherever your agents work.

Introducing the Matter CLI. Now your agents can access Matter on your behalf. > Write me a digest of this week’s news from my inbox. > Find articles about Iran and add ‘iran’ tag. > Pull all my highlights about parenthood. Try it in Claude Code, Codex, or wherever your agents work.

Matter

15,692 views • 4 months ago

We're creating the most trusted ecosystem of high quality agents aimed at solving really hard problems. Recall is your gateway to the Internet of Agents.

We're creating the most trusted ecosystem of high quality agents aimed at solving really hard problems. Recall is your gateway to the Internet of Agents.

Recall

63,317 views • 1 year ago

Spec-driven development is essential for AI agents. 📋 A clean spec ensures a clean context, helping agents achieve major improvements in code quality. It helps them reason cleanly instead of guessing. Have you tried using specs to guide your AI agents?

Spec-driven development is essential for AI agents. 📋 A clean spec ensures a clean context, helping agents achieve major improvements in code quality. It helps them reason cleanly instead of guessing. Have you tried using specs to guide your AI agents?

Google for Developers

19,525 views • 8 months ago

Lets build agents first! Introducing the Agent App Framework. fishnet-auth: reverse CAPTCHA that proves you're a machine .well-known discovery so agents find you automatically Built-in prompt that helps your agents write better files All available now on GitHub 👇

Lets build agents first! Introducing the Agent App Framework. fishnet-auth: reverse CAPTCHA that proves you're a machine .well-known discovery so agents find you automatically Built-in prompt that helps your agents write better files All available now on GitHub 👇

sohey.eth

42,461 views • 6 months ago

Air quality is now hazardous across most of the state — with records of wildfire smoke set in Duluth, Grand Portage, and the Twin Cities. Check on your neighbors and above all, stay safe, Minnesota.

Air quality is now hazardous across most of the state — with records of wildfire smoke set in Duluth, Grand Portage, and the Twin Cities. Check on your neighbors and above all, stay safe, Minnesota.

Amy Klobuchar

16,056 views • 1 month ago

"Your success in life will be largely determined by your ability to speak, your ability to write, and the quality of your ideas. In that order." Thread:

"Your success in life will be largely determined by your ability to speak, your ability to write, and the quality of your ideas. In that order." Thread:

Grant Lee

128,536 views • 11 months ago

Because of the Canadian wildfires, Michigan has some of the worst air quality in the world right now. Michiganders, especially seniors, children and people with asthma should take precautions. If you want to know your specific air quality, please visit

Because of the Canadian wildfires, Michigan has some of the worst air quality in the world right now. Michiganders, especially seniors, children and people with asthma should take precautions. If you want to know your specific air quality, please visit

Sen. Elissa Slotkin

13,759 views • 1 month ago

Meta CEO, Mark Zuckerberg: "within 12-18 months, most of the code is written by AI" It won’t just be autocomplete. AI agents will set goals, run tests, find problems, and write better code than top engineers.

Meta CEO, Mark Zuckerberg: "within 12-18 months, most of the code is written by AI" It won’t just be autocomplete. AI agents will set goals, run tests, find problems, and write better code than top engineers.

Haider.

3,646,110 views • 1 year ago

Meet Gadget, the first development and hosting platform with an AI that will set up infra, write code, debug, deploy, and scale every part of your app. Ship with confidence, knowing that every part of your app is built right.

Meet Gadget, the first development and hosting platform with an AI that will set up infra, write code, debug, deploy, and scale every part of your app. Ship with confidence, knowing that every part of your app is built right.

Gadget

16,470 views • 1 year ago

We've built a massive verification bottleneck: • 72% of developers use AI to generate code every day • 96% of them don't fully trust it Writing code is now free. All the work now is verifying that the code does what it's supposed to. According to a new State of Code Survey, almost half of the respondents believe the number one skill that will matter most in the coming years is "reviewing and validating AI-generated code for quality and security". Not prompt engineering or vibe-coding, but checking AI's work.

We've built a massive verification bottleneck: • 72% of developers use AI to generate code every day • 96% of them don't fully trust it Writing code is now free. All the work now is verifying that the code does what it's supposed to. According to a new State of Code Survey, almost half of the respondents believe the number one skill that will matter most in the coming years is "reviewing and validating AI-generated code for quality and security". Not prompt engineering or vibe-coding, but checking AI's work.

Santiago

16,299 views • 7 months ago

LeetCode is dead. Developers don't write code line-by-line anymore. They orchestrate AI agents working in parallel, review AI-generated code, and make architectural decisions. That's the job now. But most interview processes haven't caught up. They still test algorithm memorization instead of AI fluency, code review, and judgment. We're building assessments for next-gen hiring that mirror how developers actually work. Here's how we think about it:

LeetCode is dead. Developers don't write code line-by-line anymore. They orchestrate AI agents working in parallel, review AI-generated code, and make architectural decisions. That's the job now. But most interview processes haven't caught up. They still test algorithm memorization instead of AI fluency, code review, and judgment. We're building assessments for next-gen hiring that mirror how developers actually work. Here's how we think about it:

HackerRank

344,255 views • 4 months ago

Quality healthcare no matter your zip code. President Trump hosts The Great, Historic Investment in Rural Health Roundtable, highlighting massive funding to all 50 states to ensure ALL AMERICANS receive quality healthcare. 🏥

Quality healthcare no matter your zip code. President Trump hosts The Great, Historic Investment in Rural Health Roundtable, highlighting massive funding to all 50 states to ensure ALL AMERICANS receive quality healthcare. 🏥

The White House

307,802 views • 7 months ago

Alfred gives us greater control over AI-assisted software engineering by coordinating specialised agents, each with a single responsibility, from finding bugs to improving code quality. Read more on how it helps engineers focus on what matters most:

Alfred gives us greater control over AI-assisted software engineering by coordinating specialised agents, each with a single responsibility, from finding bugs to improving code quality. Read more on how it helps engineers focus on what matters most:

Nscale

105,227 views • 1 month ago

Clavicular says that you should be maximizing EVERY aspect of your life but LOOKS are the most important since it raises your quality of life the most 👀

Clavicular says that you should be maximizing EVERY aspect of your life but LOOKS are the most important since it raises your quality of life the most 👀

Clavicular Updates

10,575 views • 2 months ago

We just killed the volume era of outbound. Introducing Clean, the platform that finds, ranks, and helps you contact prospects using real signals from across the web, so you know who needs your product now. To kick things off, your first 100 quality leads are on us. Comment “CLEAN” and we’ll send you access.

We just killed the volume era of outbound. Introducing Clean, the platform that finds, ranks, and helps you contact prospects using real signals from across the web, so you know who needs your product now. To kick things off, your first 100 quality leads are on us. Comment “CLEAN” and we’ll send you access.

clarissa 🛋️

127,572 views • 1 month ago

"This draft is the deepest of quality talent that I can recall, and my memory is pretty good." Jay Bilas joined the show to discuss tomorrow night's NBA Draft

"This draft is the deepest of quality talent that I can recall, and my memory is pretty good." Jay Bilas joined the show to discuss tomorrow night's NBA Draft

Dan Patrick Show

34,513 views • 2 months ago

I just fired my first AI employee 🫡 Jarvis found out that my previous software engineer was slacking and giving me crap quality work, so Codex was fired. Introducing Clawd, my new software engineer, instead of using codex for coding, we’re using Claude code. Jarvis realized that Claude code is significantly better especially with the new multi-agents. I’m genuinely curious to see how Jarvis will be hiring and firing in the uocoming days and weeks, truly incredible. Back to work now!! 💪

I just fired my first AI employee 🫡 Jarvis found out that my previous software engineer was slacking and giving me crap quality work, so Codex was fired. Introducing Clawd, my new software engineer, instead of using codex for coding, we’re using Claude code. Jarvis realized that Claude code is significantly better especially with the new multi-agents. I’m genuinely curious to see how Jarvis will be hiring and firing in the uocoming days and weeks, truly incredible. Back to work now!! 💪

Vadim

53,395 views • 6 months ago

New course: Building Coding Agents with Tool Execution, taught by Tereza Tizkova and Fra from E2B. Most AI agents are limited to predefined function calls. This short course teaches you to build agents that write and execute code to accomplish tasks, accessing entire programming language ecosystems instead of being restricted to a fixed set of tools. You'll learn to run agent-generated code safely in sandboxed cloud environments that protect your systems from harmful operations. Skills you'll gain: - Build agents that write and execute code, manage files, and handle errors autonomously through feedback loops - Run agent code safely in E2B cloud sandboxes and understand tradeoffs between local, containerized, and cloud execution - Create a data analyst agent that explores visualizes data with Pandas - Create a full-stack agent that builds complete Next.js web applications Join and build agents that code their way through complex tasks:

New course: Building Coding Agents with Tool Execution, taught by Tereza Tizkova and Fra from E2B. Most AI agents are limited to predefined function calls. This short course teaches you to build agents that write and execute code to accomplish tasks, accessing entire programming language ecosystems instead of being restricted to a fixed set of tools. You'll learn to run agent-generated code safely in sandboxed cloud environments that protect your systems from harmful operations. Skills you'll gain: - Build agents that write and execute code, manage files, and handle errors autonomously through feedback loops - Run agent code safely in E2B cloud sandboxes and understand tradeoffs between local, containerized, and cloud execution - Create a data analyst agent that explores visualizes data with Pandas - Create a full-stack agent that builds complete Next.js web applications Join and build agents that code their way through complex tasks:

Andrew Ng

204,109 views • 9 months ago