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.
Open field noteCanonical personal archive
Field notes fromthe workbench.
Practical writing about software, Linux, open source, and AI systems. Each note keeps the language in which it was written and the context that made it useful.
The Spanish index points to this same canonical archive.
- Notes
- 14
- English
- 06
- Spanish
- 08
- Current page
- 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.
Open field noteOpenAI 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.
Open field noteAgent 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.
Open field noteMy first new AUR package contribution
My experience uploading the relagit package to the Arch User Repository, including PKGBUILD creation, testing, and publishing.
Open field noteHow 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.
Open field note