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。

AI has completely changed how code gets written. Models can now generate thousands of lines in minutes. That speed is exciting but it also creates a new problem... reviews are slow. Context is missing. Bugs slip through. The bottleneck isn’t writing code anymore, it’s understanding and shipping it safely.... show more

Shruti

165,417 subscribers

49,398 次观看 • 8 个月前 •via X (Twitter)

Anya Rossi• Live Now

Private livecam show

0 条评论

暂无评论

原始帖子的评论将显示在这里

相关视频

Reviewing AI-generated code is the new bottleneck. Writing code was slow before. Now, in a few minutes, you can generate virtually unlimited lines of code using AI. But developers are now spending 70% of their time checking that code. That's the new bottleneck. I've been using Cline, and they have a feature that actually helps with this: You can click a button and have Cline generate an inline explanation for every single line of AI-generated code. Take a look at the attached video. What it does: 1. You can read the code and the explanation together 2. You don't lose context while reviewing code 3. You understand the "why" behind each change And here is the best part: It works on any git diff. You can use it to review PRs, understand commits from other people, or catch up on a codebase you haven't touched in a while.

Reviewing AI-generated code is the new bottleneck. Writing code was slow before. Now, in a few minutes, you can generate virtually unlimited lines of code using AI. But developers are now spending 70% of their time checking that code. That's the new bottleneck. I've been using Cline, and they have a feature that actually helps with this: You can click a button and have Cline generate an inline explanation for every single line of AI-generated code. Take a look at the attached video. What it does: 1. You can read the code and the explanation together 2. You don't lose context while reviewing code 3. You understand the "why" behind each change And here is the best part: It works on any git diff. You can use it to review PRs, understand commits from other people, or catch up on a codebase you haven't touched in a while.

Santiago

64,398 次观看 • 6 个月前

CodeRabbit IDE extension is now available, it offers FREE AI code reviews directly in your code editor and it’s super easy to use. - Works in VS Code and compatible editors (Cursor, Windsurf) - supports all programming languages - catches 95%+ bugs with context-aware reviews - provides senior-level review feedback on each commit - catches defects that code gen tools often miss - enables one-click fixes for identified issues - transfers context to your code gen assistants How to use 👇

CodeRabbit IDE extension is now available, it offers FREE AI code reviews directly in your code editor and it’s super easy to use. - Works in VS Code and compatible editors (Cursor, Windsurf) - supports all programming languages - catches 95%+ bugs with context-aware reviews - provides senior-level review feedback on each commit - catches defects that code gen tools often miss - enables one-click fixes for identified issues - transfers context to your code gen assistants How to use 👇

AshutoshShrivastava

17,537 次观看 • 1 年前

Most PRs look clean at first glance…but the bugs that hurt are usually hiding in the edges. I’ve been using CodeRabbit to close that gap during PR reviews. It reads the diff, understands the context, and leaves inline comments on issues that are easy to miss in a quick skim. Sign up at → What it’s caught for me: • Logic bugs that looked harmless • Missing checks that would’ve caused runtime crashes • Edge cases I wouldn’t hit locally • Issues before they ever reached prod My flow now is basically: Open PR → Review with CodeRabbit → Merge with confidence. If you ship fast, this helps you ship safer without slowing down.

Most PRs look clean at first glance…but the bugs that hurt are usually hiding in the edges. I’ve been using CodeRabbit to close that gap during PR reviews. It reads the diff, understands the context, and leaves inline comments on issues that are easy to miss in a quick skim. Sign up at → What it’s caught for me: • Logic bugs that looked harmless • Missing checks that would’ve caused runtime crashes • Edge cases I wouldn’t hit locally • Issues before they ever reached prod My flow now is basically: Open PR → Review with CodeRabbit → Merge with confidence. If you ship fast, this helps you ship safer without slowing down.

Mujeeb Ahmed

50,052 次观看 • 5 个月前

Today, I'm excited to launch Entelligence AI DeepReviews, the next generation AI-powered code reviews. Vibe coded PRs are not production ready often creating more subtle bugs throughout the codebase than before. Entelligence fixes this by understanding the entire codebase and flags bugs, regressions, and breakages across files before you ship. But it goes beyond review comments: ✅ Auto-generated docs with architecture diagrams ✅ Team Insights to improve process, not just code ✅ Real time code reviews within your editor If you're building or leading a dev team, this is what smarter, context-aware reviews look like. Try it out in the link below 👇

Today, I'm excited to launch Entelligence AI DeepReviews, the next generation AI-powered code reviews. Vibe coded PRs are not production ready often creating more subtle bugs throughout the codebase than before. Entelligence fixes this by understanding the entire codebase and flags bugs, regressions, and breakages across files before you ship. But it goes beyond review comments: ✅ Auto-generated docs with architecture diagrams ✅ Team Insights to improve process, not just code ✅ Real time code reviews within your editor If you're building or leading a dev team, this is what smarter, context-aware reviews look like. Try it out in the link below 👇

Aiswarya Sankar

95,962 次观看 • 1 年前

"The one thing that's going to be truly future proof is judgment. What is the biggest challenge when you have a thousand AI engineers writing code? AI slop. In an era when you can do everything, the question is which of these things matter. On the engineer side, it is evaluating the code. Which of this code is even valuable? You can have AI engineers writing beautiful code that could be wrong, that could have bugs in it, that could be vulnerable. Someone needs to review it. Make sure to have a human review at some point, especially critical code that is in the core of your system. On the product side is judgment around what needs to be built and evaluating. And similarly in design, you have to have judgment around, does it make sense in the broader design system. I think this judgment is the number one thing that humans are going to bring in an era of infinite productivity."

"The one thing that's going to be truly future proof is judgment. What is the biggest challenge when you have a thousand AI engineers writing code? AI slop. In an era when you can do everything, the question is which of these things matter. On the engineer side, it is evaluating the code. Which of this code is even valuable? You can have AI engineers writing beautiful code that could be wrong, that could have bugs in it, that could be vulnerable. Someone needs to review it. Make sure to have a human review at some point, especially critical code that is in the core of your system. On the product side is judgment around what needs to be built and evaluating. And similarly in design, you have to have judgment around, does it make sense in the broader design system. I think this judgment is the number one thing that humans are going to bring in an era of infinite productivity."

Patrick OShaughnessy

24,818 次观看 • 4 个月前

You sit down to code. You have your playlist on. Coffee’s still warm. You’re ready to build. Then it starts… You forget a syntax. You open a tab. You Google it. You end up on StackOverflow. You read three different answers. Now you’re in the docs. And suddenly, you’re 10 tabs deep and completely out of flow. Sound familiar? You didn’t stop because the problem was hard. → You stopped because your workflow broke. Too many tabs. Too many distractions. Too much time spent not coding. That’s why AugmentCode exists. It’s a smart AI tool that lives inside VS Code and helps you code faster, smoother, and with way less friction. Let me explain how it helps: 👇 1. AI THAT ACTUALLY UNDERSTANDS YOUR CODE ⚡ Most AI tools guess based on your prompt. AugmentCode reads your actual codebase and gives help that fits. It can: ✅ Explain functions ✅ Fix bugs ✅ Refactor messy logic ✅ Answer your coding questions—in real time All inside your editor. 2. INSTANT DOCUMENTATION, NO TAB-HOPPING⚡ You know when you highlight a function and have no idea what it does? Now you can just select it → press a shortcut → and boom. Documentation shows up right inside VS Code. No more Googling. No more context-switching. 3. ASK IT QUESTIONS—ABOUT YOUR OWN PROJECT ⚡ This part’s WILD. You can literally ask: → “What does this file do?” → “Where is this function used?” → “Can you simplify this logic?” And it answers based on YOUR code. No more copy-pasting into ChatGPT and explaining everything from scratch. 4. GENERATE TESTS WITHOUT THE HEADACHE ⚡ Testing is important but let’s be real, writing unit tests is no one’s favorite part. AugmentCode can generate tests for your actual functions based on their logic. Not generic boilerplate—real, usable tests. 5. YOU NEVER LEAVE VS CODE ⚡ Everything: debugging, docs, AI chat, test generation...happens inside your IDE. It’s just you, your code, and an assistant who actually helps. 6. BUILT FOR REAL DEVELOPERS ⚡ This isn’t a flashy AI toy. It’s a practical tool built for indie hackers, full-stack devs, and shipping teams. → The UX is clean. The output is useful. It just works. 🔥 AugmentCode runs 2 to 3 times faster than GitHub Copilot, making it a powerful choice for large-scale projects where speed matters. It also supports collaborative coding by offering shared context and built-in integrations with tools like Slack, helping teams communicate better. If you write code, you need this. Simple as that. 👉 Because the future of coding isn’t about replacing devs. It’s about AUGMENTING them.

You sit down to code. You have your playlist on. Coffee’s still warm. You’re ready to build. Then it starts… You forget a syntax. You open a tab. You Google it. You end up on StackOverflow. You read three different answers. Now you’re in the docs. And suddenly, you’re 10 tabs deep and completely out of flow. Sound familiar? You didn’t stop because the problem was hard. → You stopped because your workflow broke. Too many tabs. Too many distractions. Too much time spent not coding. That’s why AugmentCode exists. It’s a smart AI tool that lives inside VS Code and helps you code faster, smoother, and with way less friction. Let me explain how it helps: 👇 1. AI THAT ACTUALLY UNDERSTANDS YOUR CODE ⚡ Most AI tools guess based on your prompt. AugmentCode reads your actual codebase and gives help that fits. It can: ✅ Explain functions ✅ Fix bugs ✅ Refactor messy logic ✅ Answer your coding questions—in real time All inside your editor. 2. INSTANT DOCUMENTATION, NO TAB-HOPPING⚡ You know when you highlight a function and have no idea what it does? Now you can just select it → press a shortcut → and boom. Documentation shows up right inside VS Code. No more Googling. No more context-switching. 3. ASK IT QUESTIONS—ABOUT YOUR OWN PROJECT ⚡ This part’s WILD. You can literally ask: → “What does this file do?” → “Where is this function used?” → “Can you simplify this logic?” And it answers based on YOUR code. No more copy-pasting into ChatGPT and explaining everything from scratch. 4. GENERATE TESTS WITHOUT THE HEADACHE ⚡ Testing is important but let’s be real, writing unit tests is no one’s favorite part. AugmentCode can generate tests for your actual functions based on their logic. Not generic boilerplate—real, usable tests. 5. YOU NEVER LEAVE VS CODE ⚡ Everything: debugging, docs, AI chat, test generation...happens inside your IDE. It’s just you, your code, and an assistant who actually helps. 6. BUILT FOR REAL DEVELOPERS ⚡ This isn’t a flashy AI toy. It’s a practical tool built for indie hackers, full-stack devs, and shipping teams. → The UX is clean. The output is useful. It just works. 🔥 AugmentCode runs 2 to 3 times faster than GitHub Copilot, making it a powerful choice for large-scale projects where speed matters. It also supports collaborative coding by offering shared context and built-in integrations with tools like Slack, helping teams communicate better. If you write code, you need this. Simple as that. 👉 Because the future of coding isn’t about replacing devs. It’s about AUGMENTING them.

EyeingAI

26,587 次观看 • 1 年前

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 次观看 • 4 个月前

How are coding agents changing software engineering? Yapped for 15 minutes about new Cursor data we published, including: 1. Why lines of code is an imperfect measure of AI progress 2. Balancing intelligence/cost/speed for models 3. Code reviews with "Mega PRs" (1000+ lines)

How are coding agents changing software engineering? Yapped for 15 minutes about new Cursor data we published, including: 1. Why lines of code is an imperfect measure of AI progress 2. Balancing intelligence/cost/speed for models 3. Code reviews with "Mega PRs" (1000+ lines)

Lee Robinson

57,563 次观看 • 15 天前

Codex now has plugins and CircleCI is in the directory. 🎉 The CircleCI plugin closes that loop by pulling pipeline context directly into your agent workflow so it can find failures, classify root causes, and verify fixes without leaving Codex. Find it here:

Codex now has plugins and CircleCI is in the directory. 🎉 The CircleCI plugin closes that loop by pulling pipeline context directly into your agent workflow so it can find failures, classify root causes, and verify fixes without leaving Codex. Find it here:

CircleCI

14,849 次观看 • 1 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

30,686 次观看 • 1 年前

Introducing CodeRabbit Plugin for Claude Code! The CodeRabbit plugin for Claude Code creates an autonomous AI development workflow, helping you write and fix code without manual intervention. Type /coderabbit:review (or just say “review my code”) to get AI-powered fixes directly in your dev flow! Try it today, it’s free!

Introducing CodeRabbit Plugin for Claude Code! The CodeRabbit plugin for Claude Code creates an autonomous AI development workflow, helping you write and fix code without manual intervention. Type /coderabbit:review (or just say “review my code”) to get AI-powered fixes directly in your dev flow! Try it today, it’s free!

CodeRabbit

27,190 次观看 • 4 个月前

What they don't tell you about vibe coding: • Moltbook exposed 1.5M auth tokens. The owner hadn't written a single line of code. • Tea App leaked 72,000 government IDs. The database was just open, no sophisticated hack needed. • A researcher took control of a journalist's computer through her own vibe-coded game, without a single click. The code ran fine in all three cases, tests passed, reviews looked clean, and nothing raised a flag. That's the problem nobody is talking about. Teams are shipping faster than ever. AI writes the code. CI catches build failures. Tests catch regressions. Observability catches outages. But nobody is asking the one question that actually matters: What can an attacker do with this, right now? Because the bottleneck is no longer writing code. It's understanding what that code actually exposes once it's live. PR reviews miss auth edge cases. Unit tests don't probe broken access control. Staging environments don't simulate adversarial behavior. And business logic flaws look completely fine until someone decides to break them on purpose. Strix is an open-source tool that fills this gap. It reviews your running app the way an attacker would: - Crawls the app and maps every exposed route and flow - Probes abuse paths dynamically, not just at build time - Returns findings with proof-of-concepts and suggested fixes Strix was benchmarked against 200 real companies and open-source repos, where it found 600+ verified vulnerabilities including assigned CVEs. It's designed to fit into how modern teams already work. Run it before a release, after major changes, or continuously as the app evolves. If your team is shipping AI-generated code and you don't currently have a way to answer "what does this actually expose", it's worth looking at. GitHub link in the next tweet.

What they don't tell you about vibe coding: • Moltbook exposed 1.5M auth tokens. The owner hadn't written a single line of code. • Tea App leaked 72,000 government IDs. The database was just open, no sophisticated hack needed. • A researcher took control of a journalist's computer through her own vibe-coded game, without a single click. The code ran fine in all three cases, tests passed, reviews looked clean, and nothing raised a flag. That's the problem nobody is talking about. Teams are shipping faster than ever. AI writes the code. CI catches build failures. Tests catch regressions. Observability catches outages. But nobody is asking the one question that actually matters: What can an attacker do with this, right now? Because the bottleneck is no longer writing code. It's understanding what that code actually exposes once it's live. PR reviews miss auth edge cases. Unit tests don't probe broken access control. Staging environments don't simulate adversarial behavior. And business logic flaws look completely fine until someone decides to break them on purpose. Strix is an open-source tool that fills this gap. It reviews your running app the way an attacker would: - Crawls the app and maps every exposed route and flow - Probes abuse paths dynamically, not just at build time - Returns findings with proof-of-concepts and suggested fixes Strix was benchmarked against 200 real companies and open-source repos, where it found 600+ verified vulnerabilities including assigned CVEs. It's designed to fit into how modern teams already work. Run it before a release, after major changes, or continuously as the app evolves. If your team is shipping AI-generated code and you don't currently have a way to answer "what does this actually expose", it's worth looking at. GitHub link in the next tweet.

Akshay 🚀

52,301 次观看 • 2 个月前

“Our biggest bottleneck is becoming the review of code, rather than the actual writing and generation of code.” Cisco CPO Jeetu Patel says code review is still super important though, because without human taste and judgment, code quickly turns into slop: “Every engineer on that team is now just a spec developer.” “They just build specs. They create markdown files. They give context to the model. They give context to the agent. And then the agent’s writing the code.” “I think, presumably, the review is going to get easier, too.” “You’ll have really crappy software that gets written if people aren’t paying attention to it. It doesn’t obviate the need for having taste, and having judgment, and having instinct, and making sure that you’re thinking about what you’re building."

“Our biggest bottleneck is becoming the review of code, rather than the actual writing and generation of code.” Cisco CPO Jeetu Patel says code review is still super important though, because without human taste and judgment, code quickly turns into slop: “Every engineer on that team is now just a spec developer.” “They just build specs. They create markdown files. They give context to the model. They give context to the agent. And then the agent’s writing the code.” “I think, presumably, the review is going to get easier, too.” “You’ll have really crappy software that gets written if people aren’t paying attention to it. It doesn’t obviate the need for having taste, and having judgment, and having instinct, and making sure that you’re thinking about what you’re building."

TBPN

11,289 次观看 • 4 个月前

AI isn’t a buzzword it’s the new backbone of business. The rules have changed. Today, the first question investors ask isn’t if you use AI, it’s how much of your business runs on it. From underwriting to inventory, agriculture to logistics, AI is doing in seconds what used to take weeks. And the market knows it. Ignore these tools, and someone else will beat you on cost, speed, and scale.

AI isn’t a buzzword it’s the new backbone of business. The rules have changed. Today, the first question investors ask isn’t if you use AI, it’s how much of your business runs on it. From underwriting to inventory, agriculture to logistics, AI is doing in seconds what used to take weeks. And the market knows it. Ignore these tools, and someone else will beat you on cost, speed, and scale.

Kevin O'Leary aka Mr. Wonderful

32,774 次观看 • 4 个月前

📁 Andrej Karpathy, AI researcher and former Head of AI at Tesla, says most apps today are already obsolete at birth. Because software is dissolving in front of us. You used to need code, interfaces, logic. Now it’s just an image and a prompt… and the network does everything. The shift isn’t speed. It’s that we no longer know what is still “software” at all.

📁 Andrej Karpathy, AI researcher and former Head of AI at Tesla, says most apps today are already obsolete at birth. Because software is dissolving in front of us. You used to need code, interfaces, logic. Now it’s just an image and a prompt… and the network does everything. The shift isn’t speed. It’s that we no longer know what is still “software” at all.

Jon Hernandez

27,052 次观看 • 1 个月前

$OpenAI Greg Brockman says the fraction of code not written by AI is vanishing With the right context and structure, the actual coding is already better handled by AI than by humans "what's left for human experts is the architecture" But the actual writing of code is essentially all AI now$

OpenAI Greg Brockman says the fraction of code not written by AI is vanishing With the right context and structure, the actual coding is already better handled by AI than by humans "what's left for human experts is the architecture" But the actual writing of code is essentially all AI now

Haider.

11,059 次观看 • 1 个月前

well thats fucking it - anthropic has officially replaced software engineers. claude is now a 24 hr autonomous coding agent. claude can now operate your entire computer and CLAUDE CODE = end-to-end software engineering: - claude writes the code for you - then literally opens the app it coded - clicks through the entire app and find bugs - then fixes the bugs and improves the app in hours. previously claude generated code, you run it and give claude feedback. thats completely gone now. all in a continuous loop without leaving your terminal 😂 we're barely through monday. well done lol

well thats fucking it - anthropic has officially replaced software engineers. claude is now a 24 hr autonomous coding agent. claude can now operate your entire computer and CLAUDE CODE = end-to-end software engineering: - claude writes the code for you - then literally opens the app it coded - clicks through the entire app and find bugs - then fixes the bugs and improves the app in hours. previously claude generated code, you run it and give claude feedback. thats completely gone now. all in a continuous loop without leaving your terminal 😂 we're barely through monday. well done lol

Ejaaz

1,156,137 次观看 • 2 个月前