ML

Electrobun and WGPU: Tiny, cross-platform games and ML with Bun
10 points | 3 comments

Fastest LLM decode engine on Apple Silicon. 658 tok/s on M4-max,beats mlx by 19%
5 points | 3 comments

Show HN: AvaKill – Deterministic safety firewall for AI agents (<1ms, no ML)
3 points | 3 comments

The Shift from ML Engineering to AI Engineering
3 points | 2 comments

Building a TikZ library for ML researchers
3 points | 0 comments

System Design and ML Interview Material
2 points | 0 comments

OpenFelix – Open-source AI assistant for macOS (local MLX and any cloud model)
2 points | 0 comments