Better Context, Less Chaos: How I Deal With LLM Nondeterminism
Reading Siddhant Khare's AI fatigue article made me question my own workflow. This is the approach I use to get less random output from LLMs.
Abrir nota de campoArchivo personal canónico
Notas de campo desdeel banco de trabajo.
Escritura práctica sobre software, Linux, código abierto y sistemas de IA. Cada nota conserva el idioma en que fue escrita y el contexto que la hizo útil.
El índice en inglés apunta a este mismo archivo canónico.
- Notas
- 14
- Inglés
- 06
- Español
- 08
- Página actual
- 01 / 03
OpenMemory: The Long-Term Memory Your AI Agents Actually Deserve
OpenMemory is a free, local, open-source cognitive memory engine that turns your AI agents from goldfish into assistants with real memory. Here's how I use it with MCP and OpenCode.
Abrir nota de campoOpenAI WebSocket Mode: The Secret to Ultra-Fast AI Agents
Discover how OpenAI's new WebSocket mode is transforming agentic loops by slashing latency and making multi-step reasoning 40% faster.
Abrir nota de campoAgent Skills: Giving AI Agents a Memory for Tasks
Exploring skills.sh, a new way to give AI agents standardized, reusable capabilities and make their actions more predictable.
Abrir nota de campoMy first new AUR package contribution
My experience uploading the relagit package to the Arch User Repository, including PKGBUILD creation, testing, and publishing.
Abrir nota de campoHow to Add Vercel/Analytics to Vitepress Projects
Quick tutorial on configuring Vercel Analytics for VitePress projects by adding the tracking script to your config file.
Abrir nota de campo