Video yükleniyor...

Video Yüklenemedi

Ana Sayfaya Dön

Here's how I use Gemini 2.5 Pro to write code. Yes, it's better than Claude.

BHolmesDev's profile picture

Ben Holmes

34,276 subscribers

25,334 görüntüleme • 1 yıl önce •via X (Twitter)

EğitimBilim & TeknolojiSanat
LIVE

Anya Rossi• Live Now

Private livecam show

6 Yorum

Jason Laster profil fotoğrafı
Jason Laster1 yıl önce

Nice! I love the separate planning step with o3. Have you considered adding a verification step to the flow? Basically tsc + vitest… I’d love to be able to walk away and get a PR when it’s done with the nice commits.

Ben Holmes profil fotoğrafı
Ben Holmes1 yıl önce

Ah yeah we encourage o3 to add a testing step to the plan. Gemini did come back with that rec to run tsc —noemit, but I expected it to run that autonomously tbh. You could add “make a PR on my behalf” using rules:

Nico Baier profil fotoğrafı
Nico Baier1 yıl önce

Do a full youtube video

Ben Holmes profil fotoğrafı
Ben Holmes1 yıl önce

What else do you want to see? Could upload this as is honestly

Sagar Patil profil fotoğrafı
Sagar Patil1 yıl önce

Will it be able to use MCP servers since all of them are command based?

Ben Holmes profil fotoğrafı
Ben Holmes1 yıl önce

👀

Benzer Videolar

The pace at which Gemini 2.5 Pro is improving in code is wild! I generally leaned towards using Claude for code, but now I rely more on Gemini 2.5 Pro. It's just that good! Watch me use Gemini-2.5-Pro-05-06 to go from a YT video to an interactive slide deck app in minutes!
8:23

The pace at which Gemini 2.5 Pro is improving in code is wild! I generally leaned towards using Claude for code, but now I rely more on Gemini 2.5 Pro. It's just that good! Watch me use Gemini-2.5-Pro-05-06 to go from a YT video to an interactive slide deck app in minutes!

elvis

81,882 görüntüleme • 1 yıl önce

Anthropic just dropped Claude Opus 4.1 It outperforms OpenAI o3, Gemini 2.5 Pro and Qwen-3 Coder on agentic coding and tool use. Claude Code is going to get incredibly better.
0:26

Anthropic just dropped Claude Opus 4.1 It outperforms OpenAI o3, Gemini 2.5 Pro and Qwen-3 Coder on agentic coding and tool use. Claude Code is going to get incredibly better.

Shubham Saboo

26,252 görüntüleme • 10 ay önce

My most-used AI tool isn’t ChatGPT, Claude, or Gemini. It’s Sider AI Sider with Gemini 2.5 Pro. These are my top use cases and why I prefer Sider 👇 1/10 Sider AI + Gemini 2.5 Pro is my favorite way to get insights from arXiv papers.
0:22

My most-used AI tool isn’t ChatGPT, Claude, or Gemini. It’s Sider AI Sider with Gemini 2.5 Pro. These are my top use cases and why I prefer Sider 👇 1/10 Sider AI + Gemini 2.5 Pro is my favorite way to get insights from arXiv papers.

AshutoshShrivastava

36,284 görüntüleme • 1 yıl önce

We’re releasing an updated Gemini 2.5 Pro (I/O edition) to make it even better at coding. 🚀 You can build richer web apps, games, simulations and more - all with one prompt. In Google Gemini, here's how it transformed images of nature into code to represent unique patterns 🌱
0:29

We’re releasing an updated Gemini 2.5 Pro (I/O edition) to make it even better at coding. 🚀 You can build richer web apps, games, simulations and more - all with one prompt. In Google Gemini, here's how it transformed images of nature into code to represent unique patterns 🌱

Google DeepMind

854,160 görüntüleme • 1 yıl önce

Watch how Gemini 3 Flash compares to 2.5 Pro when generating SVG code and simple web apps. ↓
0:59

Watch how Gemini 3 Flash compares to 2.5 Pro when generating SVG code and simple web apps. ↓

Google DeepMind

57,669 görüntüleme • 6 ay önce

Gemini 2.5 Pro SwiftUI Fireworks Animation. I will share the code here:
0:32

Gemini 2.5 Pro SwiftUI Fireworks Animation. I will share the code here:

Amos Gyamfi

23,980 görüntüleme • 1 yıl önce

Claude Code is now included in the Claude Pro plan which means Pro plan subscribers can use their rate limits for Claude apps and Claude Code! To celebrate, here's a conversation with Claude Code's founding engineer, Boris Cherny, on: - how we use Claude Code at Anthropic - underrated tips for using it effectively - the future of coding tools - and more!
20:43

Claude Code is now included in the Claude Pro plan which means Pro plan subscribers can use their rate limits for Claude apps and Claude Code! To celebrate, here's a conversation with Claude Code's founding engineer, Boris Cherny, on: - how we use Claude Code at Anthropic - underrated tips for using it effectively - the future of coding tools - and more!

Alex Albert

123,686 görüntüleme • 1 yıl önce

This guy literally shows how to use Claude Code 10x better
4:52

This guy literally shows how to use Claude Code 10x better

Wise

131,203 görüntüleme • 2 ay önce

Frontier-level performance, 3x faster than 2.5 Pro. Here's what to know about Gemini 3 Flash, from @TulseeDoshi ⚡
1:50

Frontier-level performance, 3x faster than 2.5 Pro. Here's what to know about Gemini 3 Flash, from @TulseeDoshi ⚡

Google

161,966 görüntüleme • 6 ay önce

Gemini 2.5 Pro is unlocking really exciting use cases at the intersection of coding and math. I remember my excitement when I first learned about the Mandelbrot set as a kid. Check out the code the Gemini 2.5 Pro model wrote given the prompt “p5js to explore a Mandelbrot set”!
0:46

Gemini 2.5 Pro is unlocking really exciting use cases at the intersection of coding and math. I remember my excitement when I first learned about the Mandelbrot set as a kid. Check out the code the Gemini 2.5 Pro model wrote given the prompt “p5js to explore a Mandelbrot set”!

Jeff Dean

18,996 görüntüleme • 1 yıl önce

Using the wrong AI model for your project? Here's how to pick between Claude 4 and Gemini 2.5 Pro: - For coding complex apps: Use Claude 4 Opus with extended thinking mode. - For everyday content creation: Use Claude 4 Sonnet for humanized, engaging copy. - For budget-friendly projects with large context: Use Gemini 2.5 Pro at $1.25 vs Claude's $15 per million tokens. - For autonomous agent tasks: Claude 4 wins with MCP integration and browser control. - For simple drawing apps: Both work, but Claude creates more advanced functionality. Save this video, you'll never pick the wrong AI model again. Want the SOP? DM me. 💬
16:05

Using the wrong AI model for your project? Here's how to pick between Claude 4 and Gemini 2.5 Pro: - For coding complex apps: Use Claude 4 Opus with extended thinking mode. - For everyday content creation: Use Claude 4 Sonnet for humanized, engaging copy. - For budget-friendly projects with large context: Use Gemini 2.5 Pro at $1.25 vs Claude's $15 per million tokens. - For autonomous agent tasks: Claude 4 wins with MCP integration and browser control. - For simple drawing apps: Both work, but Claude creates more advanced functionality. Save this video, you'll never pick the wrong AI model again. Want the SOP? DM me. 💬

Julian Goldie SEO

11,883 görüntüleme • 1 yıl önce

Claude Code creator: "I don't prompt Claude anymore. I write loops - and the loops do the work. My job is to write loops." in 30 minutes Boris reveals his actual daily Claude Code setup. Claude Code + loops + dynamic workflow Worth more than a $500 vibe-coding course
29:51

Claude Code creator: "I don't prompt Claude anymore. I write loops - and the loops do the work. My job is to write loops." in 30 minutes Boris reveals his actual daily Claude Code setup. Claude Code + loops + dynamic workflow Worth more than a $500 vibe-coding course

Codez

864,823 görüntüleme • 14 gün önce

How to Use Claude to Write Killer YouTube Scripts
9:23

How to Use Claude to Write Killer YouTube Scripts

Bryan Ng

26,706 görüntüleme • 1 ay önce

The most effective technique I've found to improve Claude Code's output is 20 years old: Write a failing test first. Here's how I use it:
5:19

The most effective technique I've found to improve Claude Code's output is 20 years old: Write a failing test first. Here's how I use it:

Matt Pocock

94,072 görüntüleme • 3 ay önce

Claude 3.7 Sonnet has serious competition! Gemini 2.5 Pro is a legit good model for code. - code quality is really good - 1M token context - native multimodality - long code generation - understand large codebases I used it with Windsurf to generate an AI search agent app:
7:18

Claude 3.7 Sonnet has serious competition! Gemini 2.5 Pro is a legit good model for code. - code quality is really good - 1M token context - native multimodality - long code generation - understand large codebases I used it with Windsurf to generate an AI search agent app:

elvis

211,476 görüntüleme • 1 yıl önce

How To Use Claude Code For Beginners
6:51

How To Use Claude Code For Beginners

corbin

48,701 görüntüleme • 2 ay önce

how it feels to use claude code.
0:53

how it feels to use claude code.

signüll

13,423 görüntüleme • 11 ay önce

Claude Code isn't just for Anthropic subscriptions anymore. How to use Claude Code with Venice:
8:41

Claude Code isn't just for Anthropic subscriptions anymore. How to use Claude Code with Venice:

Venice

25,146 görüntüleme • 4 ay önce

Model update: Gemini 2.5 Pro is now even better at coding! The new version `gemini-2.5-pro-preview-05-06` is great for building more complex apps with high-quality, visually appealing UI with fewer prompts. Here's a fun personal finance app it built:
0:39

Model update: Gemini 2.5 Pro is now even better at coding! The new version `gemini-2.5-pro-preview-05-06` is great for building more complex apps with high-quality, visually appealing UI with fewer prompts. Here's a fun personal finance app it built:

Patrick Loeber

84,504 görüntüleme • 1 yıl önce

Skills allow you to extend Claude Code in new ways using pre-packaged instructions and code. For example, add the docx skill to let Claude Code create word documents. I think skills make Claude Code even better as a general purpose agent, I'm excited to see how you use them!
0:26

Skills allow you to extend Claude Code in new ways using pre-packaged instructions and code. For example, add the docx skill to let Claude Code create word documents. I think skills make Claude Code even better as a general purpose agent, I'm excited to see how you use them!

Thariq

127,899 görüntüleme • 8 ay önce