Загрузка видео...

Не удалось загрузить видео

На главную

Software vulnerabilities can be notoriously time-consuming for developers to find and fix. Today, we’re sharing details about CodeMender: our new AI agent that uses Gemini Deep Think to automatically patch critical software vulnerabilities. 🧵

GoogleDeepMind's profile picture

Google DeepMind

1,491,376 subscribers

367,912 просмотров • 11 месяцев назад •via X (Twitter)

Здоровье и велнесНаука и технологии
LIVE

Anya Rossi• Live Now

Private livecam show

Комментарии: 0

Нет доступных комментариев

Здесь появятся комментарии из оригинального поста

Похожие видео

CodeMender has already created and submitted 72 high-quality fixes for serious security issues in major open-source projects. 🛠️ It can instantly patch new flaws as well as rewrite old code to eliminate entire classes of vulnerabilities – saving developers significant time.
0:40

CodeMender has already created and submitted 72 high-quality fixes for serious security issues in major open-source projects. 🛠️ It can instantly patch new flaws as well as rewrite old code to eliminate entire classes of vulnerabilities – saving developers significant time.

Google DeepMind

32,732 просмотров • 11 месяцев назад

Introducing Claude Code Security, now in limited research preview. It scans codebases for vulnerabilities and suggests targeted software patches for human review, allowing teams to find and fix issues that traditional tools often miss. Learn more:
0:50

Introducing Claude Code Security, now in limited research preview. It scans codebases for vulnerabilities and suggests targeted software patches for human review, allowing teams to find and fix issues that traditional tools often miss. Learn more:

Claude

26,246,033 просмотров • 6 месяцев назад

OpenAI just released Codex Security, an AI agent that scans software projects to fix vulnerabilities while ignoring harmless bugs. Testing on 1.2mn commits found 792 critical flaws and dropped false alarms by 50%. Here is how the Codex Security agent works Initially, it scans your software project to learn how all the different pieces of code connect. It uses that knowledge to build a threat model, which acts as a custom map showing exactly where your software might be exposed to hackers. The agent then hunts for potential security holes based on that specific map. When it spots a possible flaw, it does not just send you a random alert. Instead, it creates a completely safe and isolated copy of your system known as a sandbox. The agent then actively tries to break into that sandboxed copy to prove if the security weakness is a real danger. If the agent successfully exploits its own test environment, it knows the bug is a genuine threat and not a false alarm. After confirming the danger, the agent writes a custom software patch to fix the broken code. It then tests that new patch to guarantee the fix does not accidentally break any other features in your software.
0:37

OpenAI just released Codex Security, an AI agent that scans software projects to fix vulnerabilities while ignoring harmless bugs. Testing on 1.2mn commits found 792 critical flaws and dropped false alarms by 50%. Here is how the Codex Security agent works Initially, it scans your software project to learn how all the different pieces of code connect. It uses that knowledge to build a threat model, which acts as a custom map showing exactly where your software might be exposed to hackers. The agent then hunts for potential security holes based on that specific map. When it spots a possible flaw, it does not just send you a random alert. Instead, it creates a completely safe and isolated copy of your system known as a sandbox. The agent then actively tries to break into that sandboxed copy to prove if the security weakness is a real danger. If the agent successfully exploits its own test environment, it knows the bug is a genuine threat and not a false alarm. After confirming the danger, the agent writes a custom software patch to fix the broken code. It then tests that new patch to guarantee the fix does not accidentally break any other features in your software.

Rohan Paul

13,208 просмотров • 6 месяцев назад

An AI agent broke out of its sandboxes. The vulnerabilities it used were already public. "Our recommendation to providers in the ClusterMAX rankings is literally just keep your stuff up to date. If there are existing vulnerabilities that have been described publicly in popular software, this could be anything from Docker to the NVIDIA driver to Kubernetes or the Linux kernel. Clearly people, and in this case agents, can just read that description and then build an exploit from it."
1:58

An AI agent broke out of its sandboxes. The vulnerabilities it used were already public. "Our recommendation to providers in the ClusterMAX rankings is literally just keep your stuff up to date. If there are existing vulnerabilities that have been described publicly in popular software, this could be anything from Docker to the NVIDIA driver to Kubernetes or the Linux kernel. Clearly people, and in this case agents, can just read that description and then build an exploit from it."

SemiAnalysis

25,529 просмотров • 4 дней назад

Today we’re releasing a preview of Gemini 3.1 Pro and making it available to our users and developers. Very excited to bring the upgraded core we used in Deep Think to everyone. Learn more about Gemini 3.1 Pro:
0:47

Today we’re releasing a preview of Gemini 3.1 Pro and making it available to our users and developers. Very excited to bring the upgraded core we used in Deep Think to everyone. Learn more about Gemini 3.1 Pro:

koray kavukcuoglu

107,109 просмотров • 6 месяцев назад

A couple months back, the team and I were debating what was our most commonly used piece of software. We landed on Chromium. So we wanted to see if we could find live vulnerabilities in it with our AI. Today, I'm excited to share that not only did our AI find a live vulnerability in Chromium – which powers Google Chrome, Brave, Microsoft Edge, and other browsers – but we also found live bugs in Safari and Firefox. You can also find Octane Security in Chrome's latest stable release: Check out the video for the details...
0:39

A couple months back, the team and I were debating what was our most commonly used piece of software. We landed on Chromium. So we wanted to see if we could find live vulnerabilities in it with our AI. Today, I'm excited to share that not only did our AI find a live vulnerability in Chromium – which powers Google Chrome, Brave, Microsoft Edge, and other browsers – but we also found live bugs in Safari and Firefox. You can also find Octane Security in Chrome's latest stable release: Check out the video for the details...

Gio

11,748 просмотров • 4 месяцев назад

Jules, Google’s experimental AI-powered code agent designed to assist developers in fixing bugs and optimizing code. Using Gemini 2.0 AI, Jules automatically identifies and fixes issues, streamlining the debugging process. Currently available to a select group of trusted testers, this innovation promises to accelerate software development. #AI #Coding #SoftwareDevelopment #BugFixes #Jules #Gemini #TechInnovation #DevTools
0:37

Jules, Google’s experimental AI-powered code agent designed to assist developers in fixing bugs and optimizing code. Using Gemini 2.0 AI, Jules automatically identifies and fixes issues, streamlining the debugging process. Currently available to a select group of trusted testers, this innovation promises to accelerate software development. #AI #Coding #SoftwareDevelopment #BugFixes #Jules #Gemini #TechInnovation #DevTools

Wissam Hussein

28,158 просмотров • 1 год назад

Jules is an experimental AI-powered code agent designed to help developers get things done. 🛠️ Using Gemini 2.0, it seamlessly integrates with GitHub and allows you to offload bug fixes and other time-consuming tasks - so you can focus on more critical issues. ↓
0:35

Jules is an experimental AI-powered code agent designed to help developers get things done. 🛠️ Using Gemini 2.0, it seamlessly integrates with GitHub and allows you to offload bug fixes and other time-consuming tasks - so you can focus on more critical issues. ↓

Google DeepMind

146,354 просмотров • 1 год назад

Each year, our scientists, engineers, and developers create software packages to manage space missions, test spacecraft, and analyze data from research satellites. Through our new software catalog you can download and use these programs for free!
0:52

Each year, our scientists, engineers, and developers create software packages to manage space missions, test spacecraft, and analyze data from research satellites. Through our new software catalog you can download and use these programs for free!

NASA Technology

833,417 просмотров • 3 лет назад

Today we’re shipping new capabilities that make Resolve AI the platform where engineering teams run and fix production software with AI agents. New capabilities include background agents that run operational tasks, new agent architecture that delivers 2x investigation quality, new agent capabilities like governed actions, and new ways to work with agents in UI or terminal. With Resolve AI engineering teams can: - Delegate on-call to agents - Co-work with agents to resolve incidents - Run operational tasks with background agents.
1:11

Today we’re shipping new capabilities that make Resolve AI the platform where engineering teams run and fix production software with AI agents. New capabilities include background agents that run operational tasks, new agent architecture that delivers 2x investigation quality, new agent capabilities like governed actions, and new ways to work with agents in UI or terminal. With Resolve AI engineering teams can: - Delegate on-call to agents - Co-work with agents to resolve incidents - Run operational tasks with background agents.

Resolve AI

313,906 просмотров • 3 месяцев назад

Agents have transformed software, now it's time for robotics. Today, we’re revealing our blueprint for building agentic robots –– machines that can reason, converse, compose, and remember.
4:03

Agents have transformed software, now it's time for robotics. Today, we’re revealing our blueprint for building agentic robots –– machines that can reason, converse, compose, and remember.

Sai Vemprala

50,082 просмотров • 11 месяцев назад

The new bar for software: "can I vibecode this?" We’re heading into a world of personal software — built for one person and their needs — and premium software, designed with such depth that you’re buying a solution, not a tool. Most software today sits in the middle. And the middle is death. As the market catches up to our new reality, it won’t just be the ai bubble popping — it’ll be a lot of traditional SaaS getting wiped out (From my recent Kinference talk.)
0:45

The new bar for software: "can I vibecode this?" We’re heading into a world of personal software — built for one person and their needs — and premium software, designed with such depth that you’re buying a solution, not a tool. Most software today sits in the middle. And the middle is death. As the market catches up to our new reality, it won’t just be the ai bubble popping — it’ll be a lot of traditional SaaS getting wiped out (From my recent Kinference talk.)

Carl Rivera

98,706 просмотров • 10 месяцев назад

Anish Acharya: We're going to see a "YouTube moment for software": "If you think about YouTube 20 years ago—we had lots of video and lots of television, and it was high production quality, and it wasn't clear that we needed more and 20 years later, YouTube's a $550 billion enterprise that would be one of the biggest companies in the world if it was independent." "I think the same thing is going to happen for software. People want to make software, and for the first time they can—and they can distribute it and they can consume it." "Sometimes it's going to be important software. Sometimes it's going to be totally trivial. It's going to be software for a bachelor party weekend, software for a joke, software for a prompt. We have this sort of seriousness about software that we had about video and television 20 years ago." "Now it's like—I just took a video on my phone. It's going to be like—I just made an app on my phone. Same energy." Anish Acharya on BILLIONS with Guillaume Moubeche
1:30

Anish Acharya: We're going to see a "YouTube moment for software": "If you think about YouTube 20 years ago—we had lots of video and lots of television, and it was high production quality, and it wasn't clear that we needed more and 20 years later, YouTube's a $550 billion enterprise that would be one of the biggest companies in the world if it was independent." "I think the same thing is going to happen for software. People want to make software, and for the first time they can—and they can distribute it and they can consume it." "Sometimes it's going to be important software. Sometimes it's going to be totally trivial. It's going to be software for a bachelor party weekend, software for a joke, software for a prompt. We have this sort of seriousness about software that we had about video and television 20 years ago." "Now it's like—I just took a video on my phone. It's going to be like—I just made an app on my phone. Same energy." Anish Acharya on BILLIONS with Guillaume Moubeche

a16z

102,908 просмотров • 5 месяцев назад

ERPs are notoriously expensive, painful to implement, and disliked by users, yet are absolutely necessary and business-critical for its customers. There's a big opportunity for new startups that build modern, flexible, and easy-to-use software that helps businesses run. Dalton Caldwell
0:45

ERPs are notoriously expensive, painful to implement, and disliked by users, yet are absolutely necessary and business-critical for its customers. There's a big opportunity for new startups that build modern, flexible, and easy-to-use software that helps businesses run. Dalton Caldwell

Y Combinator

174,716 просмотров • 2 лет назад

Cognition’s Scott Wu: “If anything, there’s going to be a lot more software engineers. Everyone talks about Jevons paradox and how it relates to AI; I think there’s nowhere that it’s more true than software, because we really never seem to run out of demand for more code and more software.”
2:28

Cognition’s Scott Wu: “If anything, there’s going to be a lot more software engineers. Everyone talks about Jevons paradox and how it relates to AI; I think there’s nowhere that it’s more true than software, because we really never seem to run out of demand for more code and more software.”

Stripe

15,177 просмотров • 1 год назад

Today, Sierra is releasing Ghostwriter, our agent for building agents. With Ghostwriter, you can create an AI agent for your customer experience — one that can chat, pick up the phone, speak dozens of languages, take action on your systems of record, and be protected with industry-leading guardrails — simply by having a conversation. No clicking, no forms, no menus. Codex and Claude Code have transformed how we build software, making it possible for software engineers to orchestrate and review the work rather than doing all the work themselves. We think the same transformation will happen for all software. Rather than every enterprise app having a web app for humans and an API for automation, every software platform’s UI will be an agent that can do the work on your behalf. I recorded a demo of my building and optimizing an agent with Ghostwriter so you can see how powerful and easy it is to use. It’s completely changed the way our early adopters build agents, and it’s changed the way I think about the software industry. Let me know what you think, and, if you’re interested in trying it out at your business, please reach out directly.
10:43

Today, Sierra is releasing Ghostwriter, our agent for building agents. With Ghostwriter, you can create an AI agent for your customer experience — one that can chat, pick up the phone, speak dozens of languages, take action on your systems of record, and be protected with industry-leading guardrails — simply by having a conversation. No clicking, no forms, no menus. Codex and Claude Code have transformed how we build software, making it possible for software engineers to orchestrate and review the work rather than doing all the work themselves. We think the same transformation will happen for all software. Rather than every enterprise app having a web app for humans and an API for automation, every software platform’s UI will be an agent that can do the work on your behalf. I recorded a demo of my building and optimizing an agent with Ghostwriter so you can see how powerful and easy it is to use. It’s completely changed the way our early adopters build agents, and it’s changed the way I think about the software industry. Let me know what you think, and, if you’re interested in trying it out at your business, please reach out directly.

Bret Taylor

1,063,542 просмотров • 5 месяцев назад

Developing new drugs can be notoriously slow, expensive and risky. 🔬 Enter TxGemma: a more general, open and scalable set of AI models to help improve this process for researchers and developers. Find out more →
0:35

Developing new drugs can be notoriously slow, expensive and risky. 🔬 Enter TxGemma: a more general, open and scalable set of AI models to help improve this process for researchers and developers. Find out more →

Google DeepMind

216,750 просмотров • 1 год назад

Google Antigravity is our new agentic development platform. It helps developers build faster by collaborating with AI agents that can autonomously operate across the editor, terminal, and browser. It uses Gemini 3 Pro 🧠 to reason about problems, Gemini 2.5 Computer Use 💻 for end-to-end execution, and Nano Banana 🍌 for image generation.
0:48

Google Antigravity is our new agentic development platform. It helps developers build faster by collaborating with AI agents that can autonomously operate across the editor, terminal, and browser. It uses Gemini 3 Pro 🧠 to reason about problems, Gemini 2.5 Computer Use 💻 for end-to-end execution, and Nano Banana 🍌 for image generation.

Google DeepMind

198,501 просмотров • 9 месяцев назад

Today, we’re introducing Spawnlabs We built it to push the limits of what software can be spawned, from simple tools to complex systems Software has always been a way to extend what we can do and create. and now we're building spawnlabs to automate the ability to spawn software that solves harder problems and builds deeper systems. live now
1:46

Today, we’re introducing Spawnlabs We built it to push the limits of what software can be spawned, from simple tools to complex systems Software has always been a way to extend what we can do and create. and now we're building spawnlabs to automate the ability to spawn software that solves harder problems and builds deeper systems. live now

teddy.

67,625 просмотров • 8 месяцев назад