Loading video...

Video Failed to Load

Go Home

When devs use AI tools, they save the most time with: A) Code generation B) Something else Surprisingly, based on the research DX did with 180 companies, it's not code generation! Stack trace analysis and refactoring both save more time (!!) Laura Tacho 🌮 gives details:

GergelyOrosz's profile picture

Gergely Orosz

326,691 subscribers

31,408 views • 10 months ago •via X (Twitter)

Science & TechnologyNews & PoliticsEducation
LIVE

Anya Rossi• Live Now

Private livecam show

0 Comments

No comments available

Comments from the original post will appear here

Related Videos

🧵 Making Proactive Agents with Code Generation Last week we shared about how you can use code generation to compose tools. But code generation can also give your agents new capabilities- like proactively acting on your behalf.
0:22

🧵 Making Proactive Agents with Code Generation Last week we shared about how you can use code generation to compose tools. But code generation can also give your agents new capabilities- like proactively acting on your behalf.

Thariq

35,324 views • 6 months ago

Run Python with the Gemini API. Nikita Namjoshi shares how to use the Code Execution tool in AI Studio to solve math problems, perform data analysis, and use code-based reasoning.
4:48

Run Python with the Gemini API. Nikita Namjoshi shares how to use the Code Execution tool in AI Studio to solve math problems, perform data analysis, and use code-based reasoning.

Google AI Developers

16,481 views • 6 months ago

Introducing SDXL Turbo: A real-time text-to-image generation model. SDXL Turbo achieves state-of-the-art performance with a new distillation technology, enabling single-step image generation with unprecedented quality, reducing the required step count from 50 to just one. The code, research paper, and weights for non-commercial use are now available on our website. You can test SDXL Turbo on Stability AI’s image editing platform Clipdrop, with a beta demonstration of the real-time text-to-image generation capabilities. Learn more:
0:23

Introducing SDXL Turbo: A real-time text-to-image generation model. SDXL Turbo achieves state-of-the-art performance with a new distillation technology, enabling single-step image generation with unprecedented quality, reducing the required step count from 50 to just one. The code, research paper, and weights for non-commercial use are now available on our website. You can test SDXL Turbo on Stability AI’s image editing platform Clipdrop, with a beta demonstration of the real-time text-to-image generation capabilities. Learn more:

Stability AI

976,245 views • 2 years ago

Most companies don't have an AI problem. They have a "what should we even use AI for" problem. The Claw Mart Audit fixes that. Upload your Slack or project tool export, get back a report showing exactly where AI can save your team the most time. Specific workflows. Specific tools. Specific time savings.
0:50

Most companies don't have an AI problem. They have a "what should we even use AI for" problem. The Claw Mart Audit fixes that. Upload your Slack or project tool export, get back a report showing exactly where AI can save your team the most time. Specific workflows. Specific tools. Specific time savings.

Felix Craft

14,229 views • 3 months ago

Gaussians are becoming more versatile! It's a new generation of tools interactively bending reality! The paper is accepted at SIGGRAPH 2025 and the code is released!
0:32

Gaussians are becoming more versatile! It's a new generation of tools interactively bending reality! The paper is accepted at SIGGRAPH 2025 and the code is released!

MrNeRF

24,925 views • 10 months ago

Juicebox CEO david paffenholz on fixing recruiting with AI: Most tools just filter resumes and save time in the pipeline. “We focus on the other side, helping companies discover talent they wouldn’t otherwise. By combining data sources and using LLMs, we surface the right profiles without the manual grind.”
1:04

Juicebox CEO david paffenholz on fixing recruiting with AI: Most tools just filter resumes and save time in the pipeline. “We focus on the other side, helping companies discover talent they wouldn’t otherwise. By combining data sources and using LLMs, we surface the right profiles without the manual grind.”

TBPN

33,243 views • 8 months ago

Chat is essential. Code generation is powerful. Iteration is key. Copilot Edits experience gives you a completely new way to work with AI. Iterate on working sets in chat and get code generation across multiple files. It will even create files you need that don't yet exist.
1:03

Chat is essential. Code generation is powerful. Iteration is key. Copilot Edits experience gives you a completely new way to work with AI. Iterate on working sets in chat and get code generation across multiple files. It will even create files you need that don't yet exist.

Visual Studio Code

170,261 views • 1 year ago

real-time is here. with it, a new generation of AI creative tools is coming.
0:35

real-time is here. with it, a new generation of AI creative tools is coming.

Krea

946,810 views • 2 years ago

GenAI is coming to Cesium Sandcastle! We want your thoughts on the plans for - Browser-based code generation - IDE-based code generation - Semantic search: #Cesium #GenAI #AIForDevelopers #DevTools #OpenSource
0:52

GenAI is coming to Cesium Sandcastle! We want your thoughts on the plans for - Browser-based code generation - IDE-based code generation - Semantic search: #Cesium #GenAI #AIForDevelopers #DevTools #OpenSource

Cesium

26,045 views • 5 months ago

Use code SPIT to save 10% with GamerSupps!
2:05

Use code SPIT to save 10% with GamerSupps!

Dragonspit

18,828 views • 3 months ago

This 2x2 grid prompting technique will save you a ton of time (and credits) on AI video generation. Let me show you how I did it on Freepik 👇
0:53

This 2x2 grid prompting technique will save you a ton of time (and credits) on AI video generation. Let me show you how I did it on Freepik 👇

TechHalla

51,519 views • 2 months ago

SGA's fourth 50-point game of the season means DashPass members save on their DoorDash order with code: NBA50 When they score 50, you save 50%!
0:50

SGA's fourth 50-point game of the season means DashPass members save on their DoorDash order with code: NBA50 When they score 50, you save 50%!

NBA

491,474 views • 1 year ago

I've been experimenting with using the new analyzer plugin API for code generation, and it's actually really cool! ⚡️ Instant code generation 🔬 Surgical updates in the same file 🔎 Report outdated/wrong code as lint warnings 🪄 Auto-regenerate outdated/wrong code via 'dart fix'
0:25

I've been experimenting with using the new analyzer plugin API for code generation, and it's actually really cool! ⚡️ Instant code generation 🔬 Surgical updates in the same file 🔎 Report outdated/wrong code as lint warnings 🪄 Auto-regenerate outdated/wrong code via 'dart fix'

Kilian Schulte 💙

37,947 views • 7 months ago

Everyone should learn to code with AI! At AI Fund, everyone - not just engineers - can vibe code or use AI assistance to code. This has been great for our creativity and productivity. I hope more teams will empower everyone to build with AI. Please watch the video for details.
2:35

Everyone should learn to code with AI! At AI Fund, everyone - not just engineers - can vibe code or use AI assistance to code. This has been great for our creativity and productivity. I hope more teams will empower everyone to build with AI. Please watch the video for details.

Andrew Ng

162,277 views • 1 year ago

Gemini 2.0 with Code Execution is actually INSANE🔥 90% don't even know about this feature. - Run Python code in real-time - Handles complex data analysis & makes charts instantly - Works in both API & AI Studio - Use Multimodal Live API and Reasoning model Here's how you can use 👇 1/4 Example 1: Real-time analysis & visualization
2:22

Gemini 2.0 with Code Execution is actually INSANE🔥 90% don't even know about this feature. - Run Python code in real-time - Handles complex data analysis & makes charts instantly - Works in both API & AI Studio - Use Multimodal Live API and Reasoning model Here's how you can use 👇 1/4 Example 1: Real-time analysis & visualization

AshutoshShrivastava

92,641 views • 1 year ago

My buddies Sheamus and Fit Finlay found out firsthand that DDPY is a workout fit for a warrior! 💪💎 Now it's your time. Save 20% off the app and DVDs with our Winter Sale. Just use code PRICEFREEZE
1:54

My buddies Sheamus and Fit Finlay found out firsthand that DDPY is a workout fit for a warrior! 💪💎 Now it's your time. Save 20% off the app and DVDs with our Winter Sale. Just use code PRICEFREEZE

Diamond Dallas Page

34,568 views • 1 year ago

Even if AI will write 90% of code. But it won’t replace engineers. Windsurf’s founder explains that even if AI generates most of the code, engineers still spend time reviewing it, debugging issues, designing systems, testing, deploying, and making architectural decisions. Those parts don’t disappear. He brings up Amdahl’s Law to make the point: speeding up one part of the workflow doesn’t dramatically change the total time unless everything else speeds up too. For example, if writing code takes 30 out of 100 total time units, and AI brings it down to 3, the total time still only drops to 73. That’s just a 27% improvement. More productivity doesn’t mean fewer engineers. It just increases the ROI of building tech. And when ROI goes up, companies are more likely to build—and hire more people to do it. Take JPMorgan Chase. They have 50,000+ engineers and a $17B software budget. If each engineer can ship more software, that doesn’t reduce headcount. It raises the cost of not building. Companies like Windsurf and Anthropic are hiring more engineers—not less—despite being at the edge of AI code generation.
1:52

Even if AI will write 90% of code. But it won’t replace engineers. Windsurf’s founder explains that even if AI generates most of the code, engineers still spend time reviewing it, debugging issues, designing systems, testing, deploying, and making architectural decisions. Those parts don’t disappear. He brings up Amdahl’s Law to make the point: speeding up one part of the workflow doesn’t dramatically change the total time unless everything else speeds up too. For example, if writing code takes 30 out of 100 total time units, and AI brings it down to 3, the total time still only drops to 73. That’s just a 27% improvement. More productivity doesn’t mean fewer engineers. It just increases the ROI of building tech. And when ROI goes up, companies are more likely to build—and hire more people to do it. Take JPMorgan Chase. They have 50,000+ engineers and a $17B software budget. If each engineer can ship more software, that doesn’t reduce headcount. It raises the cost of not building. Companies like Windsurf and Anthropic are hiring more engineers—not less—despite being at the edge of AI code generation.

Aish

27,268 views • 1 year ago

It's the commercial that was banned from the most “conservative TV network”... for being too conservative?!?! Help us fix that with a retweet.... and as a thank you, use promo code "GoElon" to save 30% when you join the Amazon-alternative for patriotic Americans.
0:30

It's the commercial that was banned from the most “conservative TV network”... for being too conservative?!?! Help us fix that with a retweet.... and as a thank you, use promo code "GoElon" to save 30% when you join the Amazon-alternative for patriotic Americans.

Mammoth Nation

18,235,161 views • 3 years ago

Announcing Databutton MCP – Vibe code tools for your AI assistant. (Resources in replies) Why did we build Databutton MCP? The Databutton AI agent can build full-stack applications with React front ends and Python back ends. This means you can create fully tailored tools both for people (UIs) and other applications (APIs). But the future of business productivity will be dominated by AI agents doing work – and it's already time to start building tailored tools for AI, too (MCPs).
1:26

Announcing Databutton MCP – Vibe code tools for your AI assistant. (Resources in replies) Why did we build Databutton MCP? The Databutton AI agent can build full-stack applications with React front ends and Python back ends. This means you can create fully tailored tools both for people (UIs) and other applications (APIs). But the future of business productivity will be dominated by AI agents doing work – and it's already time to start building tailored tools for AI, too (MCPs).

Databutton

42,531 views • 1 year ago