LLM Engineering •
Run Kimi K3 Locally: 2.8T Params From 4 SSDs at 1 Tok/s
Run Kimi K3 locally on a MacBook by streaming 1.45TB of experts from four SSDs — the 1 tok/s number, and why doubling drives doesn't double speed.
7 min read
Read more →
Web Engineering •
Rust dyn Trait vs generics: how to switch, and the 16-byte cost
Rust dyn Trait vs generics: how to switch, and the 16-byte fat-pointer cost dyn Trait pays on every call — the cost generics compile away.
8 min read
Read more →
Web Engineering •
How to Reduce Rust Struct Memory Footprint: 5 Techniques, 56% Smaller
How to reduce Rust struct memory footprint: the 5 layout changes that shrank a real cache entry from 953 to 420 bytes, and what each one costs.
10 min read
Read more →
AI Coding Agents & DX •
Rust LSP Low Memory: How to Run Glancer Locally on 8GB RAM
Rust LSP low memory is achievable: Rust Glancer runs on 8GB machines by freezing analysis at save and offloading to disk.
8 min read
Read more →
AI Engineering •
Rust GPU Offload Without unsafe: The 400x Mistake That Isn't Safety
Rust GPU offload now works without unsafe code. Real benchmarks: 11% faster to 46% slower than CUDA on an H100, and a transfer bug that costs 400x more.
8 min read
Read more →
AI Coding Agents & DX •
Rust LLM Policy: Use AI to Review, Not to Create
The Rust LLM policy bans AI-created code and prose but allows AI review, analysis, and bug-finding. Here's the exact rule, why it works, and how to copy it.
10 min read
Read more →