Video wird geladen...

Video konnte nicht geladen werden

Zur Startseite

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)

leerob's profile picture

Lee Robinson

255,853 subscribers

57,252 Aufrufe • vor 11 Tagen •via X (Twitter)

BildungWissenschaft & Technologie
LIVE

Anya Rossi• Live Now

Private livecam show

0 Kommentare

Keine Kommentare verfügbar

Kommentare vom Original-Post werden hier angezeigt

Ähnliche Videos

Code reviews are changing forever! CodeRabbit's AI-powered platform is revolutionising how we do code reviews. Imagine a team of seasoned experts in the form of AI agents reviewing every PR that is made. 100% FREE for open-source projects.
2:16

Code reviews are changing forever! CodeRabbit's AI-powered platform is revolutionising how we do code reviews. Imagine a team of seasoned experts in the form of AI agents reviewing every PR that is made. 100% FREE for open-source projects.

Akshay 🚀

33,421 Aufrufe • vor 1 Jahr

Today, we share our AI doctor for the first time The future is an AI that knows more about your body than any human ever could. 247 commits. 140,000 lines of code. Months of engineering. Here it is:
0:37

Today, we share our AI doctor for the first time The future is an AI that knows more about your body than any human ever could. 247 commits. 140,000 lines of code. Months of engineering. Here it is:

Max Marchione

2,855,107 Aufrufe • vor 3 Monaten

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. It’s why I’ve been looking closely at tools built AI-first for this stage of the workflow. One that stands out is Graphite Agent. It sits inside your PRs and does what reviews have always struggled with at scale: → Explains logic line-by-line → Surfaces and fixes bugs → Resolves failing checks in context All without leaving the review flow.
0:32

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. It’s why I’ve been looking closely at tools built AI-first for this stage of the workflow. One that stands out is Graphite Agent. It sits inside your PRs and does what reviews have always struggled with at scale: → Explains logic line-by-line → Surfaces and fixes bugs → Resolves failing checks in context All without leaving the review flow.

Shruti

49,398 Aufrufe • vor 8 Monaten

🧲 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!
2:12

🧲 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

16,591 Aufrufe • vor 10 Monaten

Introducing @Ollama MCP AI Agents! 🎉 🔒 100% local 💻 Just 3 lines of Code 🗺️ 1000+ MCP server Integration ✨ PraisonAI v2.1 is here with 1000+ MCP Support ! Shubham Saboo Elon Musk
4:58

Introducing @Ollama MCP AI Agents! 🎉 🔒 100% local 💻 Just 3 lines of Code 🗺️ 1000+ MCP server Integration ✨ PraisonAI v2.1 is here with 1000+ MCP Support ! Shubham Saboo Elon Musk

Mervin Praison

108,860 Aufrufe • vor 1 Jahr

Windsurf proudly launches SWE-1, their first AI models designed with a comprehensive approach beyond just code. They enhance the entire software engineering process. Here's what this means for the exciting future of software engineering:
1:40

Windsurf proudly launches SWE-1, their first AI models designed with a comprehensive approach beyond just code. They enhance the entire software engineering process. Here's what this means for the exciting future of software engineering:

Fakhr

34,460 Aufrufe • vor 1 Jahr

Nubank refactors millions of lines of code with Devin, reducing a large scale ETL migration from an estimated 1.5 year project to 2 months. Devin successfully delivered 12x efficiency improvement on engineering time, helping reduce the developer toil for Nubank engineers as they’ve scaled to 110+ million customers. See why Vitor Olivier, Nubank’s CTO, is excited about the future of software engineering:
1:34

Nubank refactors millions of lines of code with Devin, reducing a large scale ETL migration from an estimated 1.5 year project to 2 months. Devin successfully delivered 12x efficiency improvement on engineering time, helping reduce the developer toil for Nubank engineers as they’ve scaled to 110+ million customers. See why Vitor Olivier, Nubank’s CTO, is excited about the future of software engineering:

Cognition

47,179 Aufrufe • vor 1 Jahr

Every AI startup is focused on "Build me an ........... app" (New projects) But what about millions of existing codebases on GitHub with billions of lines of code? To focus on existing codebases, I built a coding environment: Codespace. (Explained below)
1:16

Every AI startup is focused on "Build me an ........... app" (New projects) But what about millions of existing codebases on GitHub with billions of lines of code? To focus on existing codebases, I built a coding environment: Codespace. (Explained below)

CJ Zafir

13,832 Aufrufe • vor 9 Monaten

Cursor pays engineers $1,100,000 a year to run teams of AI agents that ship code while they sleep. [The CEO of Cursor explained in 9 minutes how they ship at 100x speed using team of agents] ↓ Save this before everyone copies the playbook 1. Engineers no longer babysit one assistant. They manage dozens of agent colleagues working in parallel, each on its own remote machine 2. Validation contract before code, not after. Humans only at scoping and review. 3. The agent team handles the full loop : planning, coding, testing, shipping PRs with each agent specialised for a role. Watch the guide. Then read the guide below by Khairallah AL-Awady
9:37

Cursor pays engineers $1,100,000 a year to run teams of AI agents that ship code while they sleep. [The CEO of Cursor explained in 9 minutes how they ship at 100x speed using team of agents] ↓ Save this before everyone copies the playbook 1. Engineers no longer babysit one assistant. They manage dozens of agent colleagues working in parallel, each on its own remote machine 2. Validation contract before code, not after. Humans only at scoping and review. 3. The agent team handles the full loop : planning, coding, testing, shipping PRs with each agent specialised for a role. Watch the guide. Then read the guide below by Khairallah AL-Awady

Avid

627,006 Aufrufe • vor 25 Tagen

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."
0:44

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 Aufrufe • vor 3 Monaten

AI Coding Agent for Hardware Optimized Code Diana AI hardware is still constrained by software. However, with reasoning models like Deepseek R1 or OpenAI o1 and o3, AI could generate hardware-optimized code that rivals—or surpasses—human CUDA code.
1:01

AI Coding Agent for Hardware Optimized Code Diana AI hardware is still constrained by software. However, with reasoning models like Deepseek R1 or OpenAI o1 and o3, AI could generate hardware-optimized code that rivals—or surpasses—human CUDA code.

Y Combinator

60,089 Aufrufe • vor 1 Jahr

I tested a new coding assistant on 34,568 lines of code. (Cursor could not achieve what this tool did.) AI models are improving every day: - Faster inference - Longer context lengths But are AI coding assistants advancing at the same rate? Can they truly understand your entire project? I tested Augment Code on my ai-engineering repo with ~35k lines of code. Augment Code is a powerful AI Assistant built for developers working with large, evolving codebases—needing an assistant that understands the full context of their projects. In the video demo below, I asked it to: - Merge two projects. - Answer a global context question. Here’s what happened: - It understood dependencies across both projects. - It merged them intelligently—without breaking anything. - It even created a README file for the merged project. - It answered my global query instantly, pulling from the full codebase. This is the difference between AI autocomplete and an AI engineer that truly understands your repo. Augment Code is powerful because it indexes your entire repo upfront. This way, it can answer questions instantly, no matter how large your project is. Lastly, Augment Code is fully compatible with VSCode, JetBrains, Vim, Slack, and more. Try them now, I have shared a link in the next tweet! Thanks to Augment Code for showing me their powerful AI coding assistant and working with me on this post.
0:31

I tested a new coding assistant on 34,568 lines of code. (Cursor could not achieve what this tool did.) AI models are improving every day: - Faster inference - Longer context lengths But are AI coding assistants advancing at the same rate? Can they truly understand your entire project? I tested Augment Code on my ai-engineering repo with ~35k lines of code. Augment Code is a powerful AI Assistant built for developers working with large, evolving codebases—needing an assistant that understands the full context of their projects. In the video demo below, I asked it to: - Merge two projects. - Answer a global context question. Here’s what happened: - It understood dependencies across both projects. - It merged them intelligently—without breaking anything. - It even created a README file for the merged project. - It answered my global query instantly, pulling from the full codebase. This is the difference between AI autocomplete and an AI engineer that truly understands your repo. Augment Code is powerful because it indexes your entire repo upfront. This way, it can answer questions instantly, no matter how large your project is. Lastly, Augment Code is fully compatible with VSCode, JetBrains, Vim, Slack, and more. Try them now, I have shared a link in the next tweet! Thanks to Augment Code for showing me their powerful AI coding assistant and working with me on this post.

Akshay 🚀

30,789 Aufrufe • vor 1 Jahr

Code review, but faster. Introducing Diffs. A new way to review PRs, directly inside Linear. • Realtime updates • Guided reviews with Al (beta) • Focused notifications • Iterate with coding agents • Threaded comments
0:51

Code review, but faster. Introducing Diffs. A new way to review PRs, directly inside Linear. • Realtime updates • Guided reviews with Al (beta) • Focused notifications • Iterate with coding agents • Threaded comments

Linear

3,619,116 Aufrufe • vor 10 Tagen

The new Factory software AI agents just combined OpenAI’s Codex, Devin, and Cursor into one product. They are fully autonomous agents called Droids that perform deep code research, technical docs, and do autonomous end-to-end coding. Here’s how it works (with real examples)👇:
0:23

The new Factory software AI agents just combined OpenAI’s Codex, Devin, and Cursor into one product. They are fully autonomous agents called Droids that perform deep code research, technical docs, and do autonomous end-to-end coding. Here’s how it works (with real examples)👇:

Alvaro Cintas

93,225 Aufrufe • vor 1 Jahr

Introducing Kombai, the first AI agent built for frontend development. Kombai vastly outperforms SOTA models + generic agents in real-world benchmarks. Watch it add a complex new feature to an OSS codebase with 500K+ lines of code. More use cases and links in comments
3:08

Introducing Kombai, the first AI agent built for frontend development. Kombai vastly outperforms SOTA models + generic agents in real-world benchmarks. Watch it add a complex new feature to an OSS codebase with 500K+ lines of code. More use cases and links in comments

Dipanjan Dey

2,074,398 Aufrufe • vor 10 Monaten

SaaS Challengers Jared Friedman AI has collapsed the cost of producing software by 10–100x, and the moat that once protected legacy SaaS, millions of lines of code built over decades, is gone. That's bad news for incumbents and great news for startups.
1:14

SaaS Challengers Jared Friedman AI has collapsed the cost of producing software by 10–100x, and the moat that once protected legacy SaaS, millions of lines of code built over decades, is gone. That's bad news for incumbents and great news for startups.

Y Combinator

396,220 Aufrufe • vor 1 Monat

How to use OSS models to beat GPT-4o performance! In 3 minutes, I go over: ◆ Explaining how Together Mixture-Of-Agents works ◆ Implementing MoA in just 50 lines of code ◆ Discussing good use cases to leverage MoA ◆ Showing off results from tests we ran
3:06

How to use OSS models to beat GPT-4o performance! In 3 minutes, I go over: ◆ Explaining how Together Mixture-Of-Agents works ◆ Implementing MoA in just 50 lines of code ◆ Discussing good use cases to leverage MoA ◆ Showing off results from tests we ran

Hassan

22,856 Aufrufe • vor 1 Jahr

Here's my conversation with the founding team of Cursor, a popular code editor (based on VSCode) that specializes in AI-assisted programming. This is a super technical conversation that is bigger than just about one code editor. It's about the future of programming and, in general, the future of human-AI collaboration. It's here on X in full, and is up on everywhere else. Timestamps: 0:00 - Introduction 0:59 - Code editor basics 3:09 - GitHub Copilot 10:27 - Cursor 16:54 - Cursor Tab 23:08 - Code diff 31:20 - ML details 36:54 - GPT vs Claude 43:28 - Prompt engineering 50:54 - AI agents 1:04:51 - Running code in background 1:09:31 - Debugging 1:14:58 - Dangerous code 1:26:09 - Branching file systems 1:29:20 - Scaling challenges 1:43:32 - Context 1:48:39 - OpenAI o1 2:00:01 - Synthetic data 2:03:48 - RLHF vs RLAIF 2:05:34 - Fields Medal for AI 2:08:17 - Scaling laws 2:17:06 - The future of programming
2:28:55

Here's my conversation with the founding team of Cursor, a popular code editor (based on VSCode) that specializes in AI-assisted programming. This is a super technical conversation that is bigger than just about one code editor. It's about the future of programming and, in general, the future of human-AI collaboration. It's here on X in full, and is up on everywhere else. Timestamps: 0:00 - Introduction 0:59 - Code editor basics 3:09 - GitHub Copilot 10:27 - Cursor 16:54 - Cursor Tab 23:08 - Code diff 31:20 - ML details 36:54 - GPT vs Claude 43:28 - Prompt engineering 50:54 - AI agents 1:04:51 - Running code in background 1:09:31 - Debugging 1:14:58 - Dangerous code 1:26:09 - Branching file systems 1:29:20 - Scaling challenges 1:43:32 - Context 1:48:39 - OpenAI o1 2:00:01 - Synthetic data 2:03:48 - RLHF vs RLAIF 2:05:34 - Fields Medal for AI 2:08:17 - Scaling laws 2:17:06 - The future of programming

Lex Fridman

1,260,683 Aufrufe • vor 1 Jahr