Загрузка видео...

Не удалось загрузить видео

На главную

New Engineering blog: We tasked Opus 4.6 using agent teams to build a C compiler. Then we (mostly) walked away. Two weeks later, it worked on the Linux kernel. Here's what it taught us about the future of autonomous software development. Read more:

AnthropicAI's profile picture

Anthropic

1,575,852 subscribers

8,524,272 просмотров • 6 месяцев назад •via X (Twitter)

ОбразованиеНовости и политикаНаука и технологии
LIVE

Anya Rossi• Live Now

Private livecam show

Комментарии: 0

Нет доступных комментариев

Здесь появятся комментарии из оригинального поста

Похожие видео

Vibecoding is great for prototypes. But what about building real components you can plug into production systems? We used Claude Opus 4.6 to build a custom TTS plugin (Kitten TTS) and hook it into Vision Agents. Here's how it works 🧵
0:32

Vibecoding is great for prototypes. But what about building real components you can plug into production systems? We used Claude Opus 4.6 to build a custom TTS plugin (Kitten TTS) and hook it into Vision Agents. Here's how it works 🧵

Stream

3,553,017 просмотров • 4 месяцев назад

🚀New Amazon Q Developer agent for software development is available to customers: This agent is based on a new agent architecture that has exciting results coming from the SWE-bench scores (on the full and verified benchmarks) representing AI models’ ability to resolve real-world coding problems. Interesting aspect of Q Agent is that with these newest updates, Q drove nearly 50% more successful coding tasks completed. What makes Q Dev Agent remarkable? The agent architecture is not just about using the best LLMs (which we do), but also giving the agent the ability to constantly explore multiple paths to find the best way to resolve a particular problem (and back tracking when it has reached dead end like a developer would do). Needless to say, we are just getting started on the developer agent and we are constantly pushing to advance our AI capabilities while maintaining quality, security, privacy, and reliability to keep Amazon Q Developer an innovative and trusted option available to our customers using agents for software development. We highlighted the results of our first SWE-bench submission of Amazon Q Developer back in June blog post; with these updates, our new agent resolves 51% more coding tasks than its previous iteration on the SWE-bench verified dataset, and 43% more on the full dataset. That’s the difference a few months make, and I can’t wait to share what our teams will deliver at re:Invent this December. Here's a quick demo showcasing our new Agent in action:
1:28

🚀New Amazon Q Developer agent for software development is available to customers: This agent is based on a new agent architecture that has exciting results coming from the SWE-bench scores (on the full and verified benchmarks) representing AI models’ ability to resolve real-world coding problems. Interesting aspect of Q Agent is that with these newest updates, Q drove nearly 50% more successful coding tasks completed. What makes Q Dev Agent remarkable? The agent architecture is not just about using the best LLMs (which we do), but also giving the agent the ability to constantly explore multiple paths to find the best way to resolve a particular problem (and back tracking when it has reached dead end like a developer would do). Needless to say, we are just getting started on the developer agent and we are constantly pushing to advance our AI capabilities while maintaining quality, security, privacy, and reliability to keep Amazon Q Developer an innovative and trusted option available to our customers using agents for software development. We highlighted the results of our first SWE-bench submission of Amazon Q Developer back in June blog post; with these updates, our new agent resolves 51% more coding tasks than its previous iteration on the SWE-bench verified dataset, and 43% more on the full dataset. That’s the difference a few months make, and I can’t wait to share what our teams will deliver at re:Invent this December. Here's a quick demo showcasing our new Agent in action:

Swami Sivasubramanian

28,946 просмотров • 1 год назад

We raised $125M to build the platform for agent engineering. Thank you to our investors (IVP, Sequoia Capital, Benchmark, Amplify Partners, Sapphire Ventures, CapitalG, and more) for their belief in us, and to our customers like Replit ⠕, Clay, Vanta, Cloudflare, Rippling, Cisco, Workday, and many more for their trust. Read more here about what this means for the future of building agents:
1:14

We raised $125M to build the platform for agent engineering. Thank you to our investors (IVP, Sequoia Capital, Benchmark, Amplify Partners, Sapphire Ventures, CapitalG, and more) for their belief in us, and to our customers like Replit ⠕, Clay, Vanta, Cloudflare, Rippling, Cisco, Workday, and many more for their trust. Read more here about what this means for the future of building agents:

LangChain

159,571 просмотров • 9 месяцев назад

Not just an April fools joke! We announced Ola Solo yesterday. It went viral and many people debated whether it’s real or an April fools joke! While the video was meant to provide a laugh to people, the technology behind it is something we’ve been working on and have prototyped. It shows the kind of pioneering work our engineering teams are capable of. Ola Solo is a glimpse into the future of mobility and our engineering teams are working on autonomous and self-balancing tech in two wheelers which you’ll see if future products from us.
0:32

Not just an April fools joke! We announced Ola Solo yesterday. It went viral and many people debated whether it’s real or an April fools joke! While the video was meant to provide a laugh to people, the technology behind it is something we’ve been working on and have prototyped. It shows the kind of pioneering work our engineering teams are capable of. Ola Solo is a glimpse into the future of mobility and our engineering teams are working on autonomous and self-balancing tech in two wheelers which you’ll see if future products from us.

Bhavish Aggarwal

940,321 просмотров • 2 лет назад

We pulled this off in just about two weeks, using a mix of tools like After Effects, TouchDesigner, Cavalry, and Blender. I’ll share the parts I worked on and some bts stuff later.
0:30

We pulled this off in just about two weeks, using a mix of tools like After Effects, TouchDesigner, Cavalry, and Blender. I’ll share the parts I worked on and some bts stuff later.

fafa

18,055 просмотров • 3 месяцев назад

"Money is a tool for reducing our uncertainty about the future. Undermining that tool raises social anxiety. Getting it back allows us to... ponder the possibilities of what we can do with the future. And it is thinking about the future that helps build civilization." 🎯
0:52

"Money is a tool for reducing our uncertainty about the future. Undermining that tool raises social anxiety. Getting it back allows us to... ponder the possibilities of what we can do with the future. And it is thinking about the future that helps build civilization." 🎯

Guy Swann

10,890 просмотров • 11 месяцев назад

Linux is the most widespread operating system, globally – but how is it built? Few people are better to answer this than Greg Kroah-Hartman (Greg K-H): Greg has been a Linux kernel maintainer for 25 years, and one of the 3 Linux Kernel Foundation Fellows (the other two are Linus Torvalds and Shuah Khan). Greg manages the Linux kernel’s stable releases, and is a maintainer of multiple kernel subsystems. We cover the inner workings of Linux kernel development, exploring everything from how changes get implemented to why its community-driven approach produces such reliable software. Greg shares insights about the kernel's unique trust model and makes a case for why engineers should contribute to open-source projects. Watch or listen: • YouTube: • Spotify: • Apple: Brought to you buy: • WorkOS — The modern identity platform for B2B SaaS. • Vanta — Automate compliance and simplify security with Vanta. Check out all of our current sponsor and their offerings: ---- One of the most surprising things I learned about Linux: although 4,000 developers contribute to the project from 500 companies per year, and has around 800 kernel maintainers, the project is run with email, git... and that's about it! No dedicated project managers, no regular meetings across the group. It's a truly fascinating and unique model (and only applies to the Linux kernel project: not to Linux distributions.) We go into more detail about this topic with Greg in the podcast as well.
0:59

Linux is the most widespread operating system, globally – but how is it built? Few people are better to answer this than Greg Kroah-Hartman (Greg K-H): Greg has been a Linux kernel maintainer for 25 years, and one of the 3 Linux Kernel Foundation Fellows (the other two are Linus Torvalds and Shuah Khan). Greg manages the Linux kernel’s stable releases, and is a maintainer of multiple kernel subsystems. We cover the inner workings of Linux kernel development, exploring everything from how changes get implemented to why its community-driven approach produces such reliable software. Greg shares insights about the kernel's unique trust model and makes a case for why engineers should contribute to open-source projects. Watch or listen: • YouTube: • Spotify: • Apple: Brought to you buy: • WorkOS — The modern identity platform for B2B SaaS. • Vanta — Automate compliance and simplify security with Vanta. Check out all of our current sponsor and their offerings: ---- One of the most surprising things I learned about Linux: although 4,000 developers contribute to the project from 500 companies per year, and has around 800 kernel maintainers, the project is run with email, git... and that's about it! No dedicated project managers, no regular meetings across the group. It's a truly fascinating and unique model (and only applies to the Linux kernel project: not to Linux distributions.) We go into more detail about this topic with Greg in the podcast as well.

Gergely Orosz

51,383 просмотров • 1 год назад

Vanta spent 7 years on this.. yet our team solved it in 2 weeks. Most companies approach integrations without thinking about it from first-principles. "Let's build our integrations library" And then commit to having large engineering teams spend years painstakingly building each integration by hand. Sure, now you can vibe code faster, but we wanted to push this a bit further... What if we didn't have to create integrations at all? What if the integrations wrote themselves? Tools like Lovable, v0, Replit are already using AI to build entire applications.. So surely building an integration "on-demand" (arguably a simpler problem) is possible. So that's what we did. We built the worlds first self-integrating system. Took Vanta 7 years to build 400 integrations. We built a million in 2 weeks.
1:52

Vanta spent 7 years on this.. yet our team solved it in 2 weeks. Most companies approach integrations without thinking about it from first-principles. "Let's build our integrations library" And then commit to having large engineering teams spend years painstakingly building each integration by hand. Sure, now you can vibe code faster, but we wanted to push this a bit further... What if we didn't have to create integrations at all? What if the integrations wrote themselves? Tools like Lovable, v0, Replit are already using AI to build entire applications.. So surely building an integration "on-demand" (arguably a simpler problem) is possible. So that's what we did. We built the worlds first self-integrating system. Took Vanta 7 years to build 400 integrations. We built a million in 2 weeks.

Claudio Fuentes

68,806 просмотров • 8 месяцев назад

Before we ship a new model, these teams try to break it. They build with it, push it to its limits, and tell us where it falls short. What they find makes the final model better.
3:12

Before we ship a new model, these teams try to break it. They build with it, push it to its limits, and tell us where it falls short. What they find makes the final model better.

Claude

593,702 просмотров • 2 месяцев назад

today we're launching the AI agent stack we built that rocketed us to a $3m AI agent consultancy. we're calling it AgentPress, and it allows you to build production grade AI agents in minutes. here's a video of me creating a sales Q&A agent
11:34

today we're launching the AI agent stack we built that rocketed us to a $3m AI agent consultancy. we're calling it AgentPress, and it allows you to build production grade AI agents in minutes. here's a video of me creating a sales Q&A agent

Andy Walters

207,205 просмотров • 11 месяцев назад

The future is not something Washington hands to us. The future is something we build, together. Today, we start building. But we can’t do it alone. This campaign belongs to all of us. Join the movement, sign up to volunteer, make a contribution if you’re able, and let’s build the future together. Let’s build:
1:37

The future is not something Washington hands to us. The future is something we build, together. Today, we start building. But we can’t do it alone. This campaign belongs to all of us. Join the movement, sign up to volunteer, make a contribution if you’re able, and let’s build the future together. Let’s build:

Shevrin “Shev” Jones

69,302 просмотров • 1 месяц назад

For ten years, Rainbow Six Siege has been more than a game. It has been a journey. Here's to the memories we created together and to the future we will continue to build.
1:36

For ten years, Rainbow Six Siege has been more than a game. It has been a journey. Here's to the memories we created together and to the future we will continue to build.

Rainbow Six Siege UK

19,314 просмотров • 8 месяцев назад

Google just released a free 2-hour+ course on full agent engineering. How to go from one prompt to a system that runs while you sleep: 38:46 - Build your first AI agent 54:46 - Connect MCP tools 1:12:43 - Run agents with four loop patterns 1:20:57 - Turn agent loops into graphs 2:22:31 - Build the complete autonomous system Most people are still building one agent and stopping there. Google is already teaching the full stack: Agents → Tools → Loops → Graphs → Autonomous Systems Single agents are the old workflow. Systems that run without you are the new one. This course is worth more than most paid agent engineering bootcamps. Bookmark and watch it today Then read the full graph engineering playbook below
2:14:04

Google just released a free 2-hour+ course on full agent engineering. How to go from one prompt to a system that runs while you sleep: 38:46 - Build your first AI agent 54:46 - Connect MCP tools 1:12:43 - Run agents with four loop patterns 1:20:57 - Turn agent loops into graphs 2:22:31 - Build the complete autonomous system Most people are still building one agent and stopping there. Google is already teaching the full stack: Agents → Tools → Loops → Graphs → Autonomous Systems Single agents are the old workflow. Systems that run without you are the new one. This course is worth more than most paid agent engineering bootcamps. Bookmark and watch it today Then read the full graph engineering playbook below

Lunar

193,416 просмотров • 6 дней назад

Introducing the Developer’s Guide to AI Agent Protocols. Stop writing custom integration glue for every tool, API, and frontend. We used Google Agent Development Kit to build a B2B agent that handles the full stack using 6 open standards: MCP, A2A, UCP, AP2, A2UI, and AG-UI The future of agents is interoperable. Read the full technical guide here:
0:35

Introducing the Developer’s Guide to AI Agent Protocols. Stop writing custom integration glue for every tool, API, and frontend. We used Google Agent Development Kit to build a B2B agent that handles the full stack using 6 open standards: MCP, A2A, UCP, AP2, A2UI, and AG-UI The future of agents is interoperable. Read the full technical guide here:

Google for Developers

116,721 просмотров • 4 месяцев назад

Re-introducing 8090... Two ways to work with us: → [BUILD] Software Factory: the platform for consulting and technology businesses building software with AI agents. The documentation stays alive because the system keeps it alive (no one ever updates the PRD on their own). → [BUY] 8090 Enterprise: AI-native custom software we design, build, and host tailored to your exact business needs. Give us a problem and we go execute. What part of your current SDLC is the most overdue for a rebuild?
3:40

Re-introducing 8090... Two ways to work with us: → [BUILD] Software Factory: the platform for consulting and technology businesses building software with AI agents. The documentation stays alive because the system keeps it alive (no one ever updates the PRD on their own). → [BUY] 8090 Enterprise: AI-native custom software we design, build, and host tailored to your exact business needs. Give us a problem and we go execute. What part of your current SDLC is the most overdue for a rebuild?

8090

301,221 просмотров • 3 месяцев назад

Demis Hassabis says AGI should become a tool before we try to make it conscious. First use it to read the language of the universe, then decide what it means to build something with agency or a mind.
1:15

Demis Hassabis says AGI should become a tool before we try to make it conscious. First use it to read the language of the universe, then decide what it means to build something with agency or a mind.

vitrupo

30,462 просмотров • 2 месяцев назад

🗺️ For ten years, Rainbow Six Siege has been more than a game. It has been a journey. Here's to the memories we created together and to the future we will continue to build.
1:36

🗺️ For ten years, Rainbow Six Siege has been more than a game. It has been a journey. Here's to the memories we created together and to the future we will continue to build.

Rainbow 6

380,608 просмотров • 8 месяцев назад