Benny Neugebauer

I collaborated with a talented Brooklyn rapper to create a song about TypeScript. Check out the amazing track we produced! 🔥 youtube.com/watch?v=3ySPR3…

Claude doesn't stick to rules...

Claude vs. Copilot

Wait… there’s a Claude FM channel on YouTube now??

@felixrieseberg Feature Request: Meta Quest support!

I'm moving and found a fun little use for Claude Cowork: Hand it a floorplan and ask it create a 3D planner. The attached demo (not my real place) was a one-shot. I also had it find all the email receipts for furniture I got over the last few years and put in matching models. Yesterday, I asked it to add a game mode so I can walk through different versions of my new place. The future is SO FUN

Introducing: the Notion Developer Platform New building blocks that help you (and your coding agents) sync any data source, build any tool, and orchestrate any agent. Follow along 👇 twitter.com/i/broadcasts/1…

🚀Rolldown 1.0 is here!🚀 Rust-based high-performance JavaScript bundler. 🏎️ Runs at native speed that’s 10~30x faster than Rollup 🤝 Compatible with existing Rollup & Vite plugins ⚡The underlying bunder for Vite 8 After 2 years, Rolldown is officially stable and has 20+M weekly downloads. Companies like Framer & PLAID are already using Rolldown in production. Thank you to every contributor, user, and team that helped us get here.

JP Morgan's investment research team just shared exactly how they built their multi-agent system "Ask David", and it's the same architecture pattern showing up everywhere: - supervisor agent orchestrates - specialized subagents handle retrieval, structured data, analytics - LLM-as-judge reflection node before the answer ships - human-in-the-loop for the last accuracy gap worth watching for anyone building:

@elonmusk is the "grokrecruiter" domain authentic?

@mpigulski @ClaudeDevs I noticed that hooks are not accurate and have delays (sound plays seconds after the prompt finished).

@bennycode @ClaudeDevs Just use a hook.

Claude Code can now send push notifications to your phone when a long task finishes or Claude needs your input. Walk away from the terminal, we'll let you know when it's done.

@sadhakbj I cursor? 😅

@bennycode What should developers who: cursor or copilot say? 😅

Should we start saying "I claude" instead of "I code"… 😅

@elonmusk Make them yellow!

Cybercab has started production

Andrej Karpathy (@karpathy), OpenAI co-founder, ex-Tesla AI, "vibe coding" creator. In just 4 mins, he explains why Claude Skills, MCP servers, and AI agents are past the hype and are now the new baseline for building. Worth every second ↓

When I'm in a bad mood I let Claude analyze my handwritten code just to read things like: "the Strategy hierarchy in particular is a textbook demonstration" 😮‍💨

@dhruvtwt_ @nvidia This is AWESOME! So, I can test free LLMS before getting myself an Nvidia Spark. :D

Why is no one talking about this? @nvidia is offering around 80 AI models via hosted APIs absolutely for free. You get access to MiniMax M2.7, GLM 5.1, Kimi 2.5, DeepSeek 3.2, GPT-OSS-120B, Sarvam-M etc. This plugs straight into OpenClaude, OpenCode, Zed IDE, Hermes agent and even with Cursor IDE. Setup: – Grab API key: build.nvidia.com/models – base_url = "integrate.api.nvidia.com/v1" – api_key = "$NVIDIA_API_KEY" – select model (e.g. minimaxai/minimax-m2.7) If you’re building or experimenting, this is basically free inference. Lock in and start building today anon. Thank me later.

@horwitzben Love it!!

I made the anti-Grammarly. Mess up your emails with AI. Sinceerly.com

Trove File Explorer on macOS is the Windows-like experience I’ve been missing. OMG! I am so happy!!

New in Claude Code: /ultrareview (research preview) runs a fleet of bug-hunting agents in the cloud. Findings land in the CLI or Desktop automatically. Run it before merging critical changes—auth, data migrations, etc. Pro and Max users get 3 free reviews through 5/5.