Hacker News
Show HN: Real-time AI (audio/video in, voice out) on an M3 Pro with Gemma E2B
Running Gemma 4 locally with LM Studio’s new headless CLI and Claude Code
The threat is comfortable drift toward not understanding what you’re doing
Components of a Coding Agent
A Rave Review of Superpowers (For Claude Code)
JSON Canvas Spec (2024)
X / Twitter
My next video will be positively awesome!
- Train sub-nano 0.1B language models on custom narrow tasks
- Write model SDKs/APIs that run blazingly fast in client machine. I'm talking 350 tok/s with 0.3GB peak memory
- How to create synthetic datasets and ship vertical SLMs
If you haven't tried Claude + Paper, it is some seriously impressive shit. All of the nicety of quick LLM design direction with a visual editor for fine-tuning.