Speedrunning an RL Environment
🔧DSPy
Flag this post
Show HN: Using GitHub Pages as zero-cost APT repository with global CDN
📦Dependency Confusion
Flag this post
I built Solveig, it turns any LLM into an assistant in your terminal. Think Claude Code with trust issues
💬AI Code Assistants
Flag this post
A portable picokernel for async I/O
🔵Go
Flag this post
Smaller Surfaces
🔧Code Refactoring Patterns
Flag this post
Linux Kernel Ported to WebAssembly
⚡WebAssembly
Flag this post
How I Use Every Claude Code Feature
💬AI Code Assistants
Flag this post
Linux/WASM
🕸️WASM
Flag this post
The Development of Pie
🏔️Alpine.js
Flag this post
Show HN: Why write code if the LLM can just do the thing? (web app experiment)
🔧Low-Code
Flag this post
IntelliJ vs. Neovim: Yak Shaving
📝Neovim
Flag this post
TIL: For long-lived LLM sessions, swapping KV Cache to RAM is ~10x faster than recalculating it. Why isn't this a standard feature?
⚡Cache Optimization
Flag this post
Loading...Loading more...