正在加载视频...

视频加载失败

加载此视频时出现问题。这可能是由于临时网络问题，或视频可能不可用。

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

11,322 subscribers

10,974 次观看 • 9 个月前 •via X (Twitter)

Anya Rossi• Live Now

Private livecam show

8 条评论

jack_cs 的头像

jack_cs9 个月前

Give a try to Devin Review - not calling it a game changer, but it's very good.

Not a Number 🎇 的头像

Not a Number 🎇9 个月前

This should be the most intuitive. Like you wouldn’t ask the same dev who wrote the PR to review their own code.

Gonzalo Sosa 的头像

Gonzalo Sosa9 个月前

What is the cost of do it that way?

Hadi Jannatabadi 的头像

Hadi Jannatabadi9 个月前

I am using same procedure and results are good

Darron Jennings 🇺🇸 的头像

Darron Jennings 🇺🇸9 个月前

This is the way!

Kirill Byvshev 的头像

Kirill Byvshev9 个月前

Reasonable

Serge Nikolaev 的头像

Serge Nikolaev9 个月前

Have you tried Copilot? Interestedwhat is better.

Ron Swanson 的头像

Ron Swanson9 个月前

Any recommendations for tools or agents that track visual changes

相关视频

Nah, this can’t be real. Same GPT-5.6 Sol. Same task. Same thinking level. I switched from regular Codex to the Claude Code harness, and the result instantly became way better. Claude Code is somehow making every model cook. GPT-5.6 SOL WAS ALREADY TOP TIER!! 😭

Nah, this can’t be real. Same GPT-5.6 Sol. Same task. Same thinking level. I switched from regular Codex to the Claude Code harness, and the result instantly became way better. Claude Code is somehow making every model cook. GPT-5.6 SOL WAS ALREADY TOP TIER!! 😭

OmedTheVibeCoder

127,040 次观看 • 3 个月前

🔥 JUST IN: Claude AI launches Code Review, where AI agents automatically review PRs for bugs.

🔥 JUST IN: Claude AI launches Code Review, where AI agents automatically review PRs for bugs.

Cointelegraph

35,319 次观看 • 7 个月前

GPT-5.2 Low just beat Opus 4.5 on a real code review. The cheapest reasoning setting caught issues the expensive model missed.

GPT-5.2 Low just beat Opus 4.5 on a real code review. The cheapest reasoning setting caught issues the expensive model missed.

Ray Fernando

48,113 次观看 • 9 个月前

Warp now supports GPT 5.2 Codex 🙌 We worked closely with the OpenAI team to tune our harness for the Codex series. GPT 5.2 Codex builds upon the strengths of GPT 5.2, excelling at long-horizon tasks (think 15 min+) Try GPT 5.2 codex and tell us what you think

Warp now supports GPT 5.2 Codex 🙌 We worked closely with the OpenAI team to tune our harness for the Codex series. GPT 5.2 Codex builds upon the strengths of GPT 5.2, excelling at long-horizon tasks (think 15 min+) Try GPT 5.2 codex and tell us what you think

Warp

33,329 次观看 • 9 个月前

Codex now runs inside JetBrains IDEs Plan, write, test, review, and ship code without leaving your code editor Starting today, you can use Codex with your ChatGPT plan in IntelliJ, PyCharm, WebStorm, and Rider, powered by GPT-5.2 Codex

Codex now runs inside JetBrains IDEs Plan, write, test, review, and ship code without leaving your code editor Starting today, you can use Codex with your ChatGPT plan in IntelliJ, PyCharm, WebStorm, and Rider, powered by GPT-5.2 Codex

OpenAI Developers

164,817 次观看 • 9 个月前

this is f**king gold someone mapped the research behind AI agents reviewing other AI agents, including 116 real coding tasks with Claude + Codex the pairing matters more than people think 1. Claude reviewing Codex pushed 71.6% → 89.7% 2. Codex self-review reached 84.5% 3. Codex reviewing Claude dropped 91.4% → 82.8% the graph connects this to self-repair, code review and multi-agent verification the takeaway is simple: the best agent is not always the best reviewer save this before letting one model write the code and approve itself

this is f**king gold someone mapped the research behind AI agents reviewing other AI agents, including 116 real coding tasks with Claude + Codex the pairing matters more than people think 1. Claude reviewing Codex pushed 71.6% → 89.7% 2. Codex self-review reached 84.5% 3. Codex reviewing Claude dropped 91.4% → 82.8% the graph connects this to self-repair, code review and multi-agent verification the takeaway is simple: the best agent is not always the best reviewer save this before letting one model write the code and approve itself

Gipp 🦅

12,632 次观看 • 2 个月前

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

1,262,281 次观看 • 1 年前

I built a new plugin! You can now trigger Codex from Claude Code! Use the Codex plugin for Claude Code to delegate tasks to Codex or have Codex review your changes using your ChatGPT subscription. Start by installing the plugin:

I built a new plugin! You can now trigger Codex from Claude Code! Use the Codex plugin for Claude Code to delegate tasks to Codex or have Codex review your changes using your ChatGPT subscription. Start by installing the plugin:

dominik kundel

1,290,869 次观看 • 6 个月前

AI can write your code. But who’s making sure it’s actually good? CodeRabbit now gives you free, high-quality AI code reviews, right inside your IDE. Supports and integrates with top AI agents like GitHub Copilot, Claude, Codex, Cursor AI, and more. What makes it different: • No subscription needed • Context-aware reviews • “Fix with AI” feature sends feedback directly to your AI coding agent • One-click commit suggestions • 10M+ PRs reviewed, 50K+ installs on GitHub Marketplace CodeRabbit doesn’t just point out issues. It helps you fix them fast.

AI can write your code. But who’s making sure it’s actually good? CodeRabbit now gives you free, high-quality AI code reviews, right inside your IDE. Supports and integrates with top AI agents like GitHub Copilot, Claude, Codex, Cursor AI, and more. What makes it different: • No subscription needed • Context-aware reviews • “Fix with AI” feature sends feedback directly to your AI coding agent • One-click commit suggestions • 10M+ PRs reviewed, 50K+ installs on GitHub Marketplace CodeRabbit doesn’t just point out issues. It helps you fix them fast.

Rohit Ghumare

32,176 次观看 • 1 年前

Today we’re releasing new Greptile review tiers: Plus and Apex. Higher tiers have more tools and subagents, can run tasks in parallel, better understand the PR, and catch more bugs. - Base: Thorough code review with full codebase context. - Plus: A deeper review for PRs that need extra scrutiny. - Apex: Our most intensive review for large, complex PRs.

Today we’re releasing new Greptile review tiers: Plus and Apex. Higher tiers have more tools and subagents, can run tasks in parallel, better understand the PR, and catch more bugs. - Base: Thorough code review with full codebase context. - Plus: A deeper review for PRs that need extra scrutiny. - Apex: Our most intensive review for large, complex PRs.

Greptile

22,150 次观看 • 1 个月前

You can now use the Claude Code and Codex harnesses directly whenever you start a cloud agent in Warp. Here's engineer Lili Wilson to show how to implement a real feature in the cloud, with computer use and automated code review to validate work:

You can now use the Claude Code and Codex harnesses directly whenever you start a cloud agent in Warp. Here's engineer Lili Wilson to show how to implement a real feature in the cloud, with computer use and automated code review to validate work:

Warp

14,055 次观看 • 5 个月前

Head of OpenAI's API: "Codex is really good at reviewing code. Codex reviews all of our PRs. It makes code reviews go from a 10-15 minute task to sometimes a 2-3 minute task, because you have a bunch of suggestions already baked in. For small PRs, you actually don't even need people to review them, we trust Codex."

Head of OpenAI's API: "Codex is really good at reviewing code. Codex reviews all of our PRs. It makes code reviews go from a 10-15 minute task to sometimes a 2-3 minute task, because you have a bunch of suggestions already baked in. For small PRs, you actually don't even need people to review them, we trust Codex."

Lenny Rachitsky

38,764 次观看 • 8 个月前

Claude Code now runs in GitLab CI/CD pipelines 🚀 Tag @ Claude in issues or merge requests to run automated coding tasks in secure containers, with all changes following your branch protection and review workflows. ✅ Available via the Anthropic API, Amazon Bedrock, and Google Vertex AI ✅ Customize Claude Code for your codebase by adding a file to your repository root ✅ Delegate code reviews, bug fixes, and implementation plans to complete routine tasks asynchronously Get started with Claude Code in GitLab:

Claude Code now runs in GitLab CI/CD pipelines 🚀 Tag @ Claude in issues or merge requests to run automated coding tasks in secure containers, with all changes following your branch protection and review workflows. ✅ Available via the Anthropic API, Amazon Bedrock, and Google Vertex AI ✅ Customize Claude Code for your codebase by adding a file to your repository root ✅ Delegate code reviews, bug fixes, and implementation plans to complete routine tasks asynchronously Get started with Claude Code in GitLab:

🦊 GitLab

33,641 次观看 • 1 年前

Why choose? Claude Code + Codex CLI running together. Same task. Or split roles. One builds, one reviews. No limits. No picking sides. On BLACKBOX.

Why choose? Claude Code + Codex CLI running together. Same task. Or split roles. One builds, one reviews. No limits. No picking sides. On BLACKBOX.

BLACKBOX AI

57,193 次观看 • 6 个月前

Developers coming from other tools are often impressed by what Codex finds in code review. In this video, Maja Trebacz and I show how to set it up and walk through issues Codex finds in real PRs. Included with ChatGPT Plus/Pro (or ~$1/run with credits).

Developers coming from other tools are often impressed by what Codex finds in code review. In this video, Maja Trebacz and I show how to set it up and walk through issues Codex finds in real PRs. Included with ChatGPT Plus/Pro (or ~$1/run with credits).

Romain Huet

176,978 次观看 • 7 个月前

Excited to release v1 of /review in the Codex CLI! You can now use gpt-5-codex to investigate and find critical bugs in your code. Check it out and let us know if you have any feedback!

Excited to release v1 of /review in the Codex CLI! You can now use gpt-5-codex to investigate and find critical bugs in your code. Check it out and let us know if you have any feedback!

daniel

743,839 次观看 • 1 年前

🧲 Meet Magnet — the AI workspace for agentic coding. Build software with Claude Code, Cursor, Codex & co. → Write a ticket → Magnet assembles context → Fires to Claude Code, Deep Research, and other agent sessions in parallel Git worktree sandboxes → PRs appear → Use agents to help you spec, research, and decompose tasks Let your agents cook!

🧲 Meet Magnet — the AI workspace for agentic coding. Build software with Claude Code, Cursor, Codex & co. → Write a ticket → Magnet assembles context → Fires to Claude Code, Deep Research, and other agent sessions in parallel Git worktree sandboxes → PRs appear → Use agents to help you spec, research, and decompose tasks Let your agents cook!

Nicolae Rusan

16,687 次观看 • 1 年前

Claude Code is no longer one AI helping you write code. It now creates full agent teams. Multiple AIs. Different roles. Shared tasks. Constant communication. All working at the same time. Like a real dev team… but automated.

Claude Code is no longer one AI helping you write code. It now creates full agent teams. Multiple AIs. Different roles. Shared tasks. Constant communication. All working at the same time. Like a real dev team… but automated.

0xMarioNawfal

62,145 次观看 • 8 个月前

Most AI coding tools still act like “one brain does everything.” Oh My Open Code flips that idea — it orchestrates multiple models like a real engineering team. Claude plans, Gemini builds, GPT reviews… all in parallel.

Most AI coding tools still act like “one brain does everything.” Oh My Open Code flips that idea — it orchestrates multiple models like a real engineering team. Claude plans, Gemini builds, GPT reviews… all in parallel.

Mervin Praison

39,392 次观看 • 9 个月前