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。

My thoughts on Grok 3 after 24hrs: - it’s really good for code - context window is HUGE - utilizes context extremely well - great at instruction following (agents!) - delightful coworker personality Here’s a 5min demo of how I’ll be using it in my code workflow going forward.

Mckay Wrigley

227,974 subscribers

2,897,314 次观看 • 1 年前 •via X (Twitter)

科学技术教育健康养生

Anya Rossi• Live Now

Private livecam show

12 条评论

Mckay Wrigley 的头像

Mckay Wrigley1 年前

As mentioned it’s the 1st non o1-pro model that works with my workflow here:

Mckay Wrigley 的头像

Mckay Wrigley1 年前

Regarding my agents comment: I threw a *ton* of highly specific instruction based prompts with all sorts of tool calls at it. Nailed every single request, even on extremely long context. So I suspect when we get API access it will be an agentic powerhouse.

Mckay Wrigley 的头像

Mckay Wrigley1 年前

It appears they may be doing some form of context truncation behind the scenes? Context summarization maybe? The web app does not error out on context until about 1M tokens, but an xAI employee says its context window is 128k tokens. This would make it 1:1 with o1 pro.

Mckay Wrigley 的头像

Mckay Wrigley1 年前

Overall I’m just thrilled to be living in a world with so many great companies making so many great models. OpenAI, Anthropic, xAI, and Google are all making exceptionally great models and I’m a very happy user/customer of each. Great multi-model world to be living in :)

Matt Figdore 的头像

Matt Figdore2 年前

This is the biggest productivity cheat code right now. Kiss reading documents goodbye. You can get an instant summary of any document with this tool.

Lorenzo 的头像

Lorenzo1 年前

@iruletheworldmo Trade talk, real-time. @XFlowChat.

John Schoenith 的头像

John Schoenith1 年前

Love RepoPrompt @pvncher

Mckay Wrigley 的头像

Mckay Wrigley1 年前

@pvncher Eric is the goat

internetVin 的头像

internetVin1 年前

This is cool. I'm excited to run my own experiments with Code Gen and grok 3. I'm assuming all of this isn't built into Cursor yet, right.

Mckay Wrigley 的头像

Mckay Wrigley1 年前

No Cursor integration just yet

Kay 的头像

Kay1 年前

grok is super underrated IMO

Mckay Wrigley 的头像

Mckay Wrigley1 年前

It’s extremely good

相关视频

Using Remix? The 1.19 release of Solidity (Wake) VS Code extension eliminates context switching. Write, test, and deploy – all in one workflow. Backed by Optimism. How does it work? Thread ↓

Using Remix? The 1.19 release of Solidity (Wake) VS Code extension eliminates context switching. Write, test, and deploy – all in one workflow. Backed by Optimism. How does it work? Thread ↓

Ackee Blockchain Security

38,512 次观看 • 11 个月前

Just gave a demo at Every 📧's Vibe Code Camp showing how I use a kanban board to stay sane while overseeing Claude Code agents😎 Here's a quick recap video showing the whole flow: 1) Monitor progress on all tasks in one view 2) See when Claude is blocked, and respond in context 3) Read Claude's plans with nice formatting, not raw Markdown 4) Use AI to process voice notes into structured tasks 5) Get explanations of code changes... with an interactive quiz to check if you understood 🙃 I've had mixed feelings about kanban workflows in the past, but as the agents get stronger I'm warming up to them—especially for churning through small well-specified tasks. In that context, it feels like the challenge is managing my working memory for what's going on. And having a stable "zoomed-out map" of all the tasks really helps me with offloading some of that cognitive load to a visualization of everything that's going on!

Just gave a demo at Every 📧's Vibe Code Camp showing how I use a kanban board to stay sane while overseeing Claude Code agents😎 Here's a quick recap video showing the whole flow: 1) Monitor progress on all tasks in one view 2) See when Claude is blocked, and respond in context 3) Read Claude's plans with nice formatting, not raw Markdown 4) Use AI to process voice notes into structured tasks 5) Get explanations of code changes... with an interactive quiz to check if you understood 🙃 I've had mixed feelings about kanban workflows in the past, but as the agents get stronger I'm warming up to them—especially for churning through small well-specified tasks. In that context, it feels like the challenge is managing my working memory for what's going on. And having a stable "zoomed-out map" of all the tasks really helps me with offloading some of that cognitive load to a visualization of everything that's going on!

Geoffrey Litt

77,993 次观看 • 4 个月前

demo of a The Browser Company AI feature for Arc manipulate websites (via code) using natural language longer video with context on Browser Co YouTube page

demo of a The Browser Company AI feature for Arc manipulate websites (via code) using natural language longer video with context on Browser Co YouTube page

Josh Miller

223,586 次观看 • 3 年前

Spec-driven development is essential for AI agents. 📋 A clean spec ensures a clean context, helping agents achieve major improvements in code quality. It helps them reason cleanly instead of guessing. Have you tried using specs to guide your AI agents?

Spec-driven development is essential for AI agents. 📋 A clean spec ensures a clean context, helping agents achieve major improvements in code quality. It helps them reason cleanly instead of guessing. Have you tried using specs to guide your AI agents?

Google for Developers

19,498 次观看 • 5 个月前

Code development often involves frequent copy & pasting of code that must be adjusted for the surrounding context. Here we describe Smart Paste, an internal tool that streamlines the code authoring workflow by automating adjustments to pasted code. More at

Code development often involves frequent copy & pasting of code that must be adjusted for the surrounding context. Here we describe Smart Paste, an internal tool that streamlines the code authoring workflow by automating adjustments to pasted code. More at

Google AI

93,402 次观看 • 2 年前

I made this interactive generative art piece using @Grok 3, purely on my iPhone. I didn’t write a single line of code. Grok 3 pretty much nailed my idea without a single error. How is this not AGI?

I made this interactive generative art piece using @Grok 3, purely on my iPhone. I didn’t write a single line of code. Grok 3 pretty much nailed my idea without a single error. How is this not AGI?

lord asado 🥩

6,386,972 次观看 • 1 年前

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:

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 次观看 • 1 年前

Documentation used to eat my context window. Two MCPs cut that to 2,800 tokens. ref tools and exa ai 🕒 Key moments 00:00 Introducing ref tools and exa ai MCPs 02:08 Configuring ref tools in Claude Code 03:27 Configuring exa ai in Claude Code 04:37 Demo: Using MCPs to upgrade a Tailwind CSS project 07:22 How to configure MCPs in Cursor 10:14 Comparing Claude Code vs. Cursor performance 12:37 Setting up MCPs for Codex 15:41 Setting up MCPs for DroidFactory 16:40 Pro-tip: How to prompt agents to use MCPs 18:00 The future of AI coding and final thoughts

Documentation used to eat my context window. Two MCPs cut that to 2,800 tokens. ref tools and exa ai 🕒 Key moments 00:00 Introducing ref tools and exa ai MCPs 02:08 Configuring ref tools in Claude Code 03:27 Configuring exa ai in Claude Code 04:37 Demo: Using MCPs to upgrade a Tailwind CSS project 07:22 How to configure MCPs in Cursor 10:14 Comparing Claude Code vs. Cursor performance 12:37 Setting up MCPs for Codex 15:41 Setting up MCPs for DroidFactory 16:40 Pro-tip: How to prompt agents to use MCPs 18:00 The future of AI coding and final thoughts

Ray Fernando

17,919 次观看 • 6 个月前

This is my annual attempt at learning how to code as a designer lol it’s always on my resolution list But hey… my code is kind of working?? It actually takes real photos?? Progress?? v0

This is my annual attempt at learning how to code as a designer lol it’s always on my resolution list But hey… my code is kind of working?? It actually takes real photos?? Progress?? v0

marisa

107,574 次观看 • 1 年前

RouteLLM is insanely good at picking the right model based on the context of the query. Easily one of my favorite features of ChatLLM, it understands the query and routes perfectly: - o1: Complex queries - gpt4o: Quick answers - sonnet: Coding - deepseek: Simple code - gemini: Long context Absolutely brilliant!

RouteLLM is insanely good at picking the right model based on the context of the query. Easily one of my favorite features of ChatLLM, it understands the query and routes perfectly: - o1: Complex queries - gpt4o: Quick answers - sonnet: Coding - deepseek: Simple code - gemini: Long context Absolutely brilliant!

AshutoshShrivastava

59,857 次观看 • 1 年前

The Context Company (The Context Company) is redefining observability for AI agents. Catch silent failures like bad tool calls, infinite loops, and hallucinations in just 10 lines of code. Congrats on the launch, Rohil Agarwal & arman!

The Context Company (The Context Company) is redefining observability for AI agents. Catch silent failures like bad tool calls, infinite loops, and hallucinations in just 10 lines of code. Congrats on the launch, Rohil Agarwal & arman!

Y Combinator

49,308 次观看 • 7 个月前

Agent Trace: Capturing the Context Graph of Code We are delighted to collaborate with Cursor, OpenCode, Vercel, Jules, Amp, Cloudflare, and Sasha Varlamov in an open standard for mapping back code:context. here's how we see the potential of code context graphs and the new era of better tooling and better agents it enables. (yes the following is vibe-videoed with Remotion's Skill and Windsurf is now Devin Desktop, 100% ai edits incl audio)

Agent Trace: Capturing the Context Graph of Code We are delighted to collaborate with Cursor, OpenCode, Vercel, Jules, Amp, Cloudflare, and Sasha Varlamov in an open standard for mapping back code:context. here's how we see the potential of code context graphs and the new era of better tooling and better agents it enables. (yes the following is vibe-videoed with Remotion's Skill and Windsurf is now Devin Desktop, 100% ai edits incl audio)

Cognition

39,670 次观看 • 4 个月前

Opus 4.6 and Codex 5.3 just launched, so I did a hexagon test on both of them Opus 4.6 - 1M context - great for research + enterprise work - agent teams + long-range reasoning - weaker on raw code benchmarks Codex 5.3 - wins coding benchmarks - faster + mid-task steering - smaller context window TLDR: Opus = depth + orchestration Codex = speed + code

Opus 4.6 and Codex 5.3 just launched, so I did a hexagon test on both of them Opus 4.6 - 1M context - great for research + enterprise work - agent teams + long-range reasoning - weaker on raw code benchmarks Codex 5.3 - wins coding benchmarks - faster + mid-task steering - smaller context window TLDR: Opus = depth + orchestration Codex = speed + code

Abhinav

447,814 次观看 • 4 个月前

Grok Code Fast 1 is versatile across the full stack and is particularly strong at TypeScript, Python, Java, Rust, C++, and Go. Using Grok Code Fast 1, Danny Limanseta built the following game in a day.

Grok Code Fast 1 is versatile across the full stack and is particularly strong at TypeScript, Python, Java, Rust, C++, and Go. Using Grok Code Fast 1, Danny Limanseta built the following game in a day.

xAI

1,075,700 次观看 • 9 个月前

This is the most insane application of MCP I've used. Context is king! Your coding agents thrive on high-quality context. Qodo Aware is a production-ready deep research agent that solves this. This is huge! Watch how I use it in Codex to retrieve context from large codebases.

This is the most insane application of MCP I've used. Context is king! Your coding agents thrive on high-quality context. Qodo Aware is a production-ready deep research agent that solves this. This is huge! Watch how I use it in Codex to retrieve context from large codebases.

elvis

80,225 次观看 • 9 个月前

How I Built ThinkAI for my client in 3 Weeks Using + Cursor I didn’t write a single line of code for this MVP. Here’s the exact process I followed to build it, FAST and efficiently.

How I Built ThinkAI for my client in 3 Weeks Using + Cursor I didn’t write a single line of code for this MVP. Here’s the exact process I followed to build it, FAST and efficiently.

Prajwal Tomar

235,107 次观看 • 1 年前

Working with Claude Code involves a lot of waiting around for Claude to figure out what it needs to complete a task. There's a better way though! Priming Claude Code with Repo Prompt context lets you get better code faster from agents like Claude Code. Let's dive in 👇

Working with Claude Code involves a lot of waiting around for Claude to figure out what it needs to complete a task. There's a better way though! Priming Claude Code with Repo Prompt context lets you get better code faster from agents like Claude Code. Let's dive in 👇

eric provencher

42,523 次观看 • 11 个月前

token efficiency isn’t just about speed, it’s also about accuracy. less noise in context == fewer hallucinations == better results. at we’ve been using call graphs + static analysis to give LLMs the best possible code context. big win not just for codegen, but for generating docs that stay true to the code itself.

token efficiency isn’t just about speed, it’s also about accuracy. less noise in context == fewer hallucinations == better results. at we’ve been using call graphs + static analysis to give LLMs the best possible code context. big win not just for codegen, but for generating docs that stay true to the code itself.

ayman nadeem

15,896 次观看 • 8 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

Just got early access to Aleph, a new in-context video model from Runway. Here’s a snippet of my first experiment using a toy car. Audio added with the MMAudio Gradio demo on Hugging Face spaces

Just got early access to Aleph, a new in-context video model from Runway. Here’s a snippet of my first experiment using a toy car. Audio added with the MMAudio Gradio demo on Hugging Face spaces

William Lamkin

79,195 次观看 • 10 个月前