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
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
The threat is comfortable drift toward not understanding what you're doing
The threat is comfortable drift toward not understanding what you're doing
Running Gemma 4 locally with LM Studio’s new headless CLI and Claude Code
Components of a Coding Agent
Components of a Coding Agent
A Rave Review of Superpowers (For Claude Code)
A Rave Review of Superpowers (For Claude Code)
JSON Canvas Spec (2024)
JSON Canvas Spec (2024)
X / Twitter
My next video will be positively awesome! Train sub-nano 0.1B language models on custom narrow tasks. Finetune on specific task/tone/voice. Unlearn all other data. All within 24 hrs of data, no GPU required. Open source implementation. Full video breakdown of the process. We've already done this, results are super promising
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.