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.
Software Engineer · Technical author
I’m Lenin AGC, a Software Engineer in Colombia. I work across web systems, open source, Linux, and AI agents. This site is where I explain what survived contact with the real problem.
Archive / recent
First-person writing from actual experiments, migrations, mistakes, and operating decisions.
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.
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.
Discover how OpenAI's new WebSocket mode is transforming agentic loops by slashing latency and making multi-step reasoning 40% faster.
Evidence routes
The profile explains the person. Repositories and product surfaces carry the implementation and their own maturity.
Contact
For collaboration, engineering work, or a concrete technical question, email and LinkedIn are the direct routes.