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.

Now in research preview: Codex Security Review It takes a deeper look at GitHub pull requests for security issues, using repository context to surface actionable findings directly in the PR. See how to enable automatic reviews:

OpenAI Developers

390,530 subscribers

285,891 views • 2 days ago •via X (Twitter)

Science & Technology Education

Anya Rossi• Live Now

Private livecam show

0 Comments

No comments available

Comments from the original post will appear here

Related Videos

We just shipped automated security reviews in Claude Code. Catch vulnerabilities before they ship with two new features: - /security-review slash command for ad-hoc security reviews - GitHub Actions integration for automatic reviews on every PR

We just shipped automated security reviews in Claude Code. Catch vulnerabilities before they ship with two new features: - /security-review slash command for ad-hoc security reviews - GitHub Actions integration for automatic reviews on every PR

Claude

1,260,166 views • 1 year ago

Agentic features in Copilot code review conduct context-aware reviews with tool calling, security integration, and the ability to hand off suggestions directly to the coding agent for implementation. 🤝 Available in all major editors while you code.

Agentic features in Copilot code review conduct context-aware reviews with tool calling, security integration, and the ability to hand off suggestions directly to the coding agent for implementation. 🤝 Available in all major editors while you code.

GitHub

34,083 views • 9 months ago

Medium-depth reviews are now in public preview for GitHub Copilot code review. Increase the effort level from low to medium so reviews route to a higher-reasoning model for more thorough analysis. 🔍 Here's how to use it ⬇️

Medium-depth reviews are now in public preview for GitHub Copilot code review. Increase the effort level from low to medium so reviews route to a higher-reasoning model for more thorough analysis. 🔍 Here's how to use it ⬇️

GitHub

68,417 views • 1 month ago

Feature development just got easier. 💻⚡ Now in preview, Amazon Q Developer integration brings AI-powered automation to GitHub. Implement new features, run code reviews on new pull requests & modernize legacy apps—all while using GitHub native issues. 👉

Feature development just got easier. 💻⚡ Now in preview, Amazon Q Developer integration brings AI-powered automation to GitHub. Implement new features, run code reviews on new pull requests & modernize legacy apps—all while using GitHub native issues. 👉

Amazon Web Services

15,311 views • 1 year ago

I stopped using the same AI to write and review code. Claude builds. GPT-5.2 Codex reviews. Result? More bugs caught, real security issues flagged, and better PRs all automated.

I stopped using the same AI to write and review code. Claude builds. GPT-5.2 Codex reviews. Result? More bugs caught, real security issues flagged, and better PRs all automated.

Mervin Praison

10,891 views • 6 months ago

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:

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

26,229,218 views • 5 months ago

Defend the enterprise. Security Forge, our new cyber security offering for source code vulnerability detection that moves at machine speed. See how Chad and George used it to autonomously scan a codebase, compress 109 flags down to 10 actionable findings, and do it for $78 — so security teams know exactly what to fix and why.

Defend the enterprise. Security Forge, our new cyber security offering for source code vulnerability detection that moves at machine speed. See how Chad and George used it to autonomously scan a codebase, compress 109 flags down to 10 actionable findings, and do it for $78 — so security teams know exactly what to fix and why.

Palantir

2,297,558 views • 1 month ago

You can now enable Codex to execute CodeRabbit directly in your development workflow! Let AI code, review, and fix issues autonomously without any human intervention 🤖 (Check out the updated CodeRabbit CLI x Codex docs below!)

You can now enable Codex to execute CodeRabbit directly in your development workflow! Let AI code, review, and fix issues autonomously without any human intervention 🤖 (Check out the updated CodeRabbit CLI x Codex docs below!)

CodeRabbit

19,201 views • 10 months ago

Now available in the Slack Marketplace — GitHub Copilot 🎉 💡 Get effortless insights: Instantly surface Copilot suggestions and code insights right inside Slack threads 🤝 Collaborate in real time: Devs, reviewers, and stakeholders can easily stay in sync without switching apps 🎁 Keep context intact: Code reviews, pull requests, and AI-powered feedback stay tied directly to your Slack workspace Grab the GitHub app on Slack Marketplace today:

Now available in the Slack Marketplace — GitHub Copilot 🎉 💡 Get effortless insights: Instantly surface Copilot suggestions and code insights right inside Slack threads 🤝 Collaborate in real time: Devs, reviewers, and stakeholders can easily stay in sync without switching apps 🎁 Keep context intact: Code reviews, pull requests, and AI-powered feedback stay tied directly to your Slack workspace Grab the GitHub app on Slack Marketplace today:

Slack

38,238 views • 9 months ago

Extensions are an integral part of Visual Studio Code - and now, Copilot functionality can be added to your extensions. See this in action with the GitHub Pull Requests extension, using Copilot to summarize issues/PRs. Available to everyone today with GitHub Copilot Free. Learn more:

Extensions are an integral part of Visual Studio Code - and now, Copilot functionality can be added to your extensions. See this in action with the GitHub Pull Requests extension, using Copilot to summarize issues/PRs. Available to everyone today with GitHub Copilot Free. Learn more:

Visual Studio Code

68,121 views • 1 year ago

Claude and Codex have a /goal skill now. But for goals to work, you need good acceptance criteria. A good process using Matt Pocock's skills: - Use /grill-with-docs to scope out the feature - Use /to-issues to turn your conversation into actionable goals as GitHub issues

Claude and Codex have a /goal skill now. But for goals to work, you need good acceptance criteria. A good process using Matt Pocock's skills: - Use /grill-with-docs to scope out the feature - Use /to-issues to turn your conversation into actionable goals as GitHub issues

Ben Holmes

39,550 views • 1 month ago

A major research project, in memory of singer Sarah Harding, will look for early signs of breast cancer in young women. Researchers hope the findings will enable all women to have a risk assessment for it at 30. Kimberley Walsh said how it would have meant the world to Sarah.

A major research project, in memory of singer Sarah Harding, will look for early signs of breast cancer in young women. Researchers hope the findings will enable all women to have a risk assessment for it at 30. Kimberley Walsh said how it would have meant the world to Sarah.

BBC Morning Live

108,898 views • 3 years ago

Announcing DiffKit: A fast, design-first GitHub dashboard for developers who want to stay on top of their pull requests, issues, and code reviews — without the noise. It's free an open-source

Announcing DiffKit: A fast, design-first GitHub dashboard for developers who want to stay on top of their pull requests, issues, and code reviews — without the noise. It's free an open-source

alan

23,825 views • 3 months ago

Claude AI Agents using Model Context Protocol (MCP) 📚 Step-by-step Hands-on Tutorial (Create ANYTHING) 🔍 How to Integrate Web Search Brave 💻 How to integrate with GitHub 🎫 It automatically Creates Issues 🔄 It automatically Creates Pull Requests 📝 It automatically summaries search results ⚡ How to Configure? Anthropic Alex Albert

Claude AI Agents using Model Context Protocol (MCP) 📚 Step-by-step Hands-on Tutorial (Create ANYTHING) 🔍 How to Integrate Web Search Brave 💻 How to integrate with GitHub 🎫 It automatically Creates Issues 🔄 It automatically Creates Pull Requests 📝 It automatically summaries search results ⚡ How to Configure? Anthropic Alex Albert

Mervin Praison

63,658 views • 1 year ago

3️⃣Project Padawan: A sneak peek at our SWE agent and how we envision these types of agents will fit into the GitHub user experience. When it’s released later this year, Project Padawan will allow you to directly assign issues to GitHub Copilot – and have it produce fully-tested pull requests. The force is strong in this one✌️ (4/4)

3️⃣Project Padawan: A sneak peek at our SWE agent and how we envision these types of agents will fit into the GitHub user experience. When it’s released later this year, Project Padawan will allow you to directly assign issues to GitHub Copilot – and have it produce fully-tested pull requests. The force is strong in this one✌️ (4/4)

Thomas Dohmke

113,180 views • 1 year ago

AI can write more code than any team can review by hand, and a pull request can look fine while hiding a security issue or missing a requirement. In our new short course, AI Code Review, built in collaboration with Qodo and taught by Nnenna 👩🏽‍💻✨, you'll learn the practices that make AI code review effective: review before you open a pull request, give the reviewer full context about your codebase, and triage findings by risk. Then you'll build your own review agent, from a context engine that finds the right code to a team of specialized reviewers. Enroll for free:

AI can write more code than any team can review by hand, and a pull request can look fine while hiding a security issue or missing a requirement. In our new short course, AI Code Review, built in collaboration with Qodo and taught by Nnenna 👩🏽‍💻✨, you'll learn the practices that make AI code review effective: review before you open a pull request, give the reviewer full context about your codebase, and triage findings by risk. Then you'll build your own review agent, from a context engine that finds the right code to a team of specialized reviewers. Enroll for free:

DeepLearning.AI

53,175 views • 10 days ago

Security Exploits have risen with the recent rise in crypto markets. Let's build a security monitoring dashboard using Messari's APIs to keep track of all major security exploits with AI insights. It takes less than 10mins. Here are the endpoints we'll be using: 1. Copilot API: 2. Events API: Prompt used to generate in Cursor: Github Repo with generated code:

Security Exploits have risen with the recent rise in crypto markets. Let's build a security monitoring dashboard using Messari's APIs to keep track of all major security exploits with AI insights. It takes less than 10mins. Here are the endpoints we'll be using: 1. Copilot API: 2. Events API: Prompt used to generate in Cursor: Github Repo with generated code:

Diran Li

22,441 views • 1 year ago

THIS GUY MADE CLAUDE CODE AND CODEX TALK TO EACH OTHER not by switching between them, they literally talk to each other about your code in real time you give it a task. it spawns a Claude agent and a Codex agent in separate sessions. they share findings, challenge each other, and produce a combined result. he pointed them at an Express API with intentional security issues. within minutes they found SQL injection, hardcoded secrets, missing auth, and weak JWT config. one catches something and the other confirms it and adds context. they divide the work on their own for faster speed one command: /collab "review auth.js for security issues" that's it. you watch the conversation happen in real time. AND its open source with new models being integrated crazy to think that this was entirely vibe coded

THIS GUY MADE CLAUDE CODE AND CODEX TALK TO EACH OTHER not by switching between them, they literally talk to each other about your code in real time you give it a task. it spawns a Claude agent and a Codex agent in separate sessions. they share findings, challenge each other, and produce a combined result. he pointed them at an Express API with intentional security issues. within minutes they found SQL injection, hardcoded secrets, missing auth, and weak JWT config. one catches something and the other confirms it and adds context. they divide the work on their own for faster speed one command: /collab "review auth.js for security issues" that's it. you watch the conversation happen in real time. AND its open source with new models being integrated crazy to think that this was entirely vibe coded

Om Patel

25,318 views • 4 months ago