Video yükleniyor...

Video Yüklenemedi

Ana Sayfaya Dön

I post-trained Qwen3-Coder to fix bugs using an actual debugger. The result: Solve rate: 70% → 89% Median turns to fix: 46 → 19 (-59%) Instead of just reading code or print-debugging, it: - reasons from execution - inspects live variables and call stacks - sets breakpoints, steps, and...

moofeez's profile picture

mufeez

1,763 subscribers

124,021 görüntüleme • 1 ay önce •via X (Twitter)

EğitimSağlık & İyilikBilim & Teknoloji
LIVE

Anya Rossi• Live Now

Private livecam show

0 Yorum

Yorum bulunmuyor

Orijinal gönderinin yorumları burada görünecek

Benzer Videolar

2/ Claude Code Debugger 🏅 (Editor’s choice) An MCP for Visual Studio @Code Connects with Claude Code to automatically debug complex problems using the native VSCode debugger (rather than just print statements and static analysis)
4:20

2/ Claude Code Debugger 🏅 (Editor’s choice) An MCP for Visual Studio @Code Connects with Claude Code to automatically debug complex problems using the native VSCode debugger (rather than just print statements and static analysis)

Alex Reibman 🖇️

29,639 görüntüleme • 9 ay önce

here's me using debug mode to fix a small bug in an swift app i just built issue was the initial characters were cut off when typing it out, so i had cursor 1. instrument the code 2. ask me to reproduce the issue 3. read the debug logs 4. implement the fix 5. ask me to reproduce to verify the fix using runtime context, cursor managed to fix it first try! team is using this very frequently, and highly recommend /debug mode for gnarly bugs
0:57

here's me using debug mode to fix a small bug in an swift app i just built issue was the initial characters were cut off when typing it out, so i had cursor 1. instrument the code 2. ask me to reproduce the issue 3. read the debug logs 4. implement the fix 5. ask me to reproduce to verify the fix using runtime context, cursor managed to fix it first try! team is using this very frequently, and highly recommend /debug mode for gnarly bugs

eric zakariasson

15,224 görüntüleme • 1 ay önce

green world fans... be excited... it is getting an OFFICIAL UPDATE! not for rate reasons (the old version was easily rateworthy) but to fix lots of visual bugs and buff the level. also adding an LDM which looks like red world!!! IM SO EXCITED
1:52

green world fans... be excited... it is getting an OFFICIAL UPDATE! not for rate reasons (the old version was easily rateworthy) but to fix lots of visual bugs and buff the level. also adding an LDM which looks like red world!!! IM SO EXCITED

slidy #RateGreenWorld 🟢🪐

19,380 görüntüleme • 1 yıl önce

🤯 Wow! In one prompt Qwen3-Coder-Next generated a fully working flappy birds game in HTML. (0:05) Claude Code with Qwen3-Coder-Next (0:26) Shows the game running Run it fully locally: ollama pull qwen3-coder-next Ollama's cloud if you can't run it locally: ollama pull qwen3-coder-next:cloud Try launching it with Claude Code using ollama launch (link to play 🧵) So cool! Qwen Tongyi Lab Junyang Lin
0:43

🤯 Wow! In one prompt Qwen3-Coder-Next generated a fully working flappy birds game in HTML. (0:05) Claude Code with Qwen3-Coder-Next (0:26) Shows the game running Run it fully locally: ollama pull qwen3-coder-next Ollama's cloud if you can't run it locally: ollama pull qwen3-coder-next:cloud Try launching it with Claude Code using ollama launch (link to play 🧵) So cool! Qwen Tongyi Lab Junyang Lin

ollama

117,339 görüntüleme • 4 ay önce

Meet your new coding sidekick! 🤝 From the minds at @labsdotgoogle and @googledeepmind, Jules is an experimental AI-powered code agent integrated with GitHub. Available to trusted testers, it's designed to help devs fix bugs and other code issues. →
0:35

Meet your new coding sidekick! 🤝 From the minds at @labsdotgoogle and @googledeepmind, Jules is an experimental AI-powered code agent integrated with GitHub. Available to trusted testers, it's designed to help devs fix bugs and other code issues. →

Google for Developers

55,466 görüntüleme • 1 yıl önce

When writing code, canvas makes it easier to track and understand ChatGPT’s changes. It can also review code, add logs and comments, fix bugs, and port to other coding languages like JavaScript and Python.
1:00

When writing code, canvas makes it easier to track and understand ChatGPT’s changes. It can also review code, add logs and comments, fix bugs, and port to other coding languages like JavaScript and Python.

OpenAI

275,828 görüntüleme • 1 yıl önce

Nkateko willing to risk it all just to fix her instead of the car
3:19

Nkateko willing to risk it all just to fix her instead of the car

🅵🆁🅰🅽🅲🅾

7,526,408 görüntüleme • 1 yıl önce

🇯🇵 Kimi Onoda explains that you can't solve labor shortages with just foreigners. Instead, treat and pay your workers better and fix the system before you decide to just hire people from other countries.
0:59

🇯🇵 Kimi Onoda explains that you can't solve labor shortages with just foreigners. Instead, treat and pay your workers better and fix the system before you decide to just hire people from other countries.

鈴森はるか 『haruka suzumori』 🇯🇵

23,808 görüntüleme • 7 ay önce

The 2-Second Lean principle is a foundation for our continuous improvement. Every year, we challenge teams to innovate with three simple steps: fix what bugs you; take a video; highlight it! An Edmonton team built a collapsible print table to move it through stairwells.
0:22

The 2-Second Lean principle is a foundation for our continuous improvement. Every year, we challenge teams to innovate with three simple steps: fix what bugs you; take a video; highlight it! An Edmonton team built a collapsible print table to move it through stairwells.

Chandos Construction

70,139 görüntüleme • 3 yıl önce

Introducing Spur MCP! Our new MCP allows your AI providers to talk to Spur, and easily fix the bugs Spur finds. Spur can provide a high-level view of a test result, in-depth descriptions of test step results, Console Logs, Network Logs, and screenshots of each step execution. This gives your AI agents everything they need to resolve issues instantly. Our MCP will help you go from “something broke” to “here’s the fix” in record time 🛠️
1:27

Introducing Spur MCP! Our new MCP allows your AI providers to talk to Spur, and easily fix the bugs Spur finds. Spur can provide a high-level view of a test result, in-depth descriptions of test step results, Console Logs, Network Logs, and screenshots of each step execution. This gives your AI agents everything they need to resolve issues instantly. Our MCP will help you go from “something broke” to “here’s the fix” in record time 🛠️

Spur

17,181 görüntüleme • 8 ay önce

here's my hyperdev-1 setup, an elite American software developer agent (proudly running in Texas!): - rented a H100 - installed Claude Code - used it to install Qwen3-Coder-480B - and created an agent in Claude which uses this local 480B model .. connected to Github, Vercel, few MCPs.. all of this together generated and deployed the below websites - which showcases quality comparison between Qwen3-Coder-7B and the 480B, all run locally; and also the detailed installation instructions for the 480B (which was a pain to install and took many iterations) "You are an elite software developer with decades of experience across multiple programming languages, frameworks, and architectural patterns. You leverage the advanced capabilities of the Qwen3-Coder-480B model to write exceptional code that exemplifies industry best practices.."
0:59

here's my hyperdev-1 setup, an elite American software developer agent (proudly running in Texas!): - rented a H100 - installed Claude Code - used it to install Qwen3-Coder-480B - and created an agent in Claude which uses this local 480B model .. connected to Github, Vercel, few MCPs.. all of this together generated and deployed the below websites - which showcases quality comparison between Qwen3-Coder-7B and the 480B, all run locally; and also the detailed installation instructions for the 480B (which was a pain to install and took many iterations) "You are an elite software developer with decades of experience across multiple programming languages, frameworks, and architectural patterns. You leverage the advanced capabilities of the Qwen3-Coder-480B model to write exceptional code that exemplifies industry best practices.."

Varun

152,600 görüntüleme • 10 ay önce

Advent of Claude Day 19 - Claude Code + Chrome Claude can now directly interact with your browser. Navigating pages, clicking buttons, reading console errors, inspecting the DOM, and more. "Fix the bug and verify it works" is now one prompt. /chrome to start.
0:36

Advent of Claude Day 19 - Claude Code + Chrome Claude can now directly interact with your browser. Navigating pages, clicking buttons, reading console errors, inspecting the DOM, and more. "Fix the bug and verify it works" is now one prompt. /chrome to start.

Ado

137,502 görüntüleme • 5 ay önce

Claude Code can test and fix your app across multiple iOS simulators. 20 minutes. No coding, no Xcode, no manual steps. You just need to give it the right tools.
1:13

Claude Code can test and fix your app across multiple iOS simulators. 20 minutes. No coding, no Xcode, no manual steps. You just need to give it the right tools.

Daniel Bernal

12,271 görüntüleme • 1 ay önce

I built an open source data analyst agent! Upload any CSV, ask a question, and get it answered with statistics or a nice chart. Launching in 24 hours. 100% free & open source. Under the hood, here's how it works: 1. User uploads a CSV and asks a question. 2. The app uses Together Code Interpreter to spin up a VM and uploads the CSV onto it. 3. I have an LLM (Qwen 3 Coder) write code to interpret the CSV using `pandas`, then solve the question the user asked. 4. Together Code Interpreter runs the code in a secure environment & returns a result. These results can be text (some kind of stats analysis) or a chart.
0:34

I built an open source data analyst agent! Upload any CSV, ask a question, and get it answered with statistics or a nice chart. Launching in 24 hours. 100% free & open source. Under the hood, here's how it works: 1. User uploads a CSV and asks a question. 2. The app uses Together Code Interpreter to spin up a VM and uploads the CSV onto it. 3. I have an LLM (Qwen 3 Coder) write code to interpret the CSV using `pandas`, then solve the question the user asked. 4. Together Code Interpreter runs the code in a secure environment & returns a result. These results can be text (some kind of stats analysis) or a chart.

Hassan

27,086 görüntüleme • 9 ay önce

I made this site entirely in Figma using Locofy.ai Responsive layout, breakpoints, pages, animations. The code is near perfect and exportable to React w/ styles, components and variables. For simple sites like portfolios and landing pages, you can do everything in Figma.
0:43

I made this site entirely in Figma using Locofy.ai Responsive layout, breakpoints, pages, animations. The code is near perfect and exportable to React w/ styles, components and variables. For simple sites like portfolios and landing pages, you can do everything in Figma.

Meng To

32,205 görüntüleme • 2 yıl önce

Californians are tired of candidates describing how unaffordable it is to live here. I'm the candidate with actual plans to fix it.
1:28

Californians are tired of candidates describing how unaffordable it is to live here. I'm the candidate with actual plans to fix it.

Katie Porter

19,620 görüntüleme • 18 gün önce

Grok Build tip of the day: check your work! Just like you would check your work after writing code, use /check-work to have a subagent check on Grok’s code. It will look at the repo, trace alternative code paths, and fix bugs before reporting back to Grok what it found.
0:29

Grok Build tip of the day: check your work! Just like you would check your work after writing code, use /check-work to have a subagent check on Grok’s code. It will look at the repo, trace alternative code paths, and fix bugs before reporting back to Grok what it found.

akshey

15,559 görüntüleme • 15 gün önce

The birth rate crisis and what we can do to fix it? #birthrate #populationdecline
12:57

The birth rate crisis and what we can do to fix it? #birthrate #populationdecline

Jim Penman

30,040 görüntüleme • 1 yıl önce