💥NEW AI CODING TUTORIAL: How To Start Claude Code Projects The Right Way (@claudeai ) TIMESTAMPS 00:00 Don't make the same mistake I did 02:30 Phase 1: PLAN 02:54 2 Questions to ask before starting 04:44 How to use AI to help you plan 06:14 Creating a project spec doc 11:36

I've been quietly impressed by the Claude Code Desktop app and how useful it is for both beginners and experienced Claude Code users. This Saturday, I'm hosting a (free) lightning lesson on @MavenHQ, where I'll share everything I've learned about how to build complete projects

I've been quietly impressed by the Claude Code Desktop app and how useful it is for both beginners and experienced Claude Code users. This Saturday, I'm hosting a (free) lightning lesson on @MavenHQ, where I'll share everything I've learned about how to build complete projects

Here's how I build every feature with Claude Code. I call it the RPIT process: Research -> Plan -> Implement -> Test Research: (Optional) Ask Claude to create a research report on any APls or new tech needed for the feature. For bigger features where Claude needs to make tech

I'll be deep diving into the RPIT build process and 23 more pro-tips, lessons, and mistakes to avoid in my upcoming Claude Code 101 lightning lesson. Sign up to attend live or get the recording: https://t.co/6uqnc2Hdbf

Here's how I build every feature with Claude Code. I call it the RPIT process: Research -> Plan -> Implement -> Test Research: (Optional) Ask Claude to create a research report on any APls or new tech needed for the feature. For bigger features where Claude needs to make tech

check out the updated skill-creator. i esp like built-in support for test generation (e.g., to measure + optimize tricky things like skill trigger rate). available in Claude Code as plugin, https://t.co/K3nY8o6Zw7, + Cowork.

Many people risk getting left behind because they think you have to use a terminal to build with Claude Code. But the truth is you can build complete projects just by using Claude Code on Desktop, Web and Mobile. I'm hosting a (free) lightning lesson on @MavenHQ where I'll

Claude Code crash course: Skills vs Plugins vs MCPs vs Commands vs Subagents vs Hooks Plugins = packages of customizations to extend Claude Code's capabilities. - Add power-user workflows from companies and tools - Installed via Marketplaces = app stores, Plugins = apps - e.g

Claude Code crash course: Skills vs Plugins vs MCPs vs Commands vs Subagents vs Hooks Plugins = packages of customizations to extend Claude Code's capabilities. - Add power-user workflows from companies and tools - Installed via Marketplaces = app stores, Plugins = apps - e.g

We've rolled out a new auto-memory feature. Claude now remembers what it learns across sessions — your project context, debugging patterns, preferred approaches — and recalls it later without you having to write anything down.

Just wrapped up the January/ February cohort of my "Ship with Claude Code and Replit" AI Coding Accelerator. I had the privilege of helping 20+ engineers, PMs, founders, and executives (CTO, CIO) from industries like tech, finance, healthcare and automotive / manufacturing.

It is hard to communicate how much programming has changed due to AI in the last 2 months: not gradually and over time in the "progress as usual" way, but specifically this last December. There are a number of asterisks but imo coding agents basically didn’t work before December

@avthar's Claude Code & Replit accelerator was a game changer. His teaching style, workflows, and the community he's built are next level. If you're using AI coding agents without this kind of guidance, you're leaving speed on the table. You and your dev team will thank you.

Introducing: built-in git worktree support for Claude Code Now, agents can run in parallel without interfering with one other. Each agent gets its own worktree and can work independently. The Claude Code Desktop app has had built-in support for worktrees for a while, and now

Sufficiently advanced agentic coding is essentially machine learning: the engineer sets up the optimization goal as well as some constraints on the search space (the spec and its tests), then an optimization process (coding agents) iterates until the goal is reached. The result

Big standout: Sonnet 4.6 can outperform Opus 4.5 "Users even preferred Sonnet 4.6 to Opus 4.5, our frontier model from November, 59% of the time. They rated Sonnet 4.6 as significantly less prone to overengineering and “laziness,” and meaningfully better at instruction

Wrapped up Ship with Claude Code & Replit with @avthar last week on @MavenHQ. Highly recommend for anyone using CC and wants to level up their workflow through hands-on experimentation and rapid iteration. If coding doesn't feeling like a creative act, you're doing it wrong.

If you or your team would like to become AI-native and ship with Claude Code and Replit, spots are open for the next cohort in April: https://t.co/lQQUZ0FBC6

Just wrapped up the January/ February cohort of my "Ship with Claude Code and Replit" AI Coding Accelerator. I had the privilege of helping 20+ engineers, PMs, founders, and executives (CTO, CIO) from industries like tech, finance, healthcare and automotive / manufacturing.

The @DarioAmodei interview. 0:00:00 - What exactly are we scaling? 0:12:36 - Is diffusion cope? 0:29:42 - Is continual learning necessary? 0:46:20 - If AGI is imminent, why not buy more compute? 0:58:49 - How will AI labs actually make profit? 1:31:19 - Will regulations destroy