Qwen 3.5 Quick Start (Then We'll Talk About Why Alibaba Just Undercut Everyone)
Qwen 3.5 dropped an hour ago. Here's how to run the 397B parameter model right now, plus why this matters for AI economics.
READ_MORE
THE ANTIDOTE TO
VIBE CODING.
WHAT_I'M_WORKING_ON
PROJECTS
IOBS
liveYour iPhone as a wireless camera and mic for OBS
Turn your iPhone into a low-latency wireless camera, microphone, or both for OBS Studio. No apps to install, no cables, works anywhere—even coffee shops.
WebRTCReactTypeScriptBun
Website
MOJO-VOICE
in devLightning-fast, privacy-first voice dictation for developers
Press a hotkey, speak naturally, and your words appear instantly at your cursor. No cloud, no latency, no compromises.
MOJORUSTCANDLEWHISPER
Website
GitHub
PLUM
stableFast, fuzzy-search TUI for discovering and installing plugins
Browse 600+ plugins from 11 marketplaces instantly. Fuzzy search, zero setup, blazing fast.
GOTUICLI
GitHub
VISAGE-MOJO
in devFoundational ML library written in Mojo from first principles
Neural networks and training algorithms implemented from scratch in Mojo. Python expressiveness with C-level performance.
MOJO
GitHub
CLAUDE-CODE-TMUX
coming soonSmooth, interactive Claude Code experience in tmux
A plugin that adds smooth and interactive experience when using Claude Code in tmux sessions.
BASHTMUX
UNTHROTTLED-AI
coming soonDecentralized AI compute marketplace for consumer hardware
Earn money from spare compute while helping build community-run AI infrastructure. No single company controls it.
RUSTWEBGPU
LATEST_TRANSMISSIONS
BLOG
NVIDIA's DMS: 8x Cheaper LLM Reasoning Without the Accuracy Tradeoff
NVIDIA's new Dynamic Memory Sparsification technique cuts LLM reasoning costs by 8x. Here's what it means for developers building AI applications.
READ_MOREOpenAI vs Anthropic: The 15-Minute Super Bowl Rivalry
Sam Altman's meltdown over Anthropic's Super Bowl ad reveals a year of escalating competition: 5 weeks to 15 minutes. The timeline nobody's talking about.
READ_MORE