Practical articles on AI, DevOps, Cloud, Linux, and infrastructure engineering.
We changed a system prompt for what we thought was a tone improvement and broke a customer-critical extraction overnight. The version control and regression tests we built next.
We had Datadog for app metrics, Loki for logs, and zero useful insight into what our LLM service was actually doing. Here's the observability stack we built specifically for model serving.
Learn how to fine-tune LLMs like Llama 2, Mistral, and GPT models for your specific use case. Includes LoRA, QLoRA, and full fine-tuning techniques.
We deploy LangChain apps in Docker on Kubernetes. The patterns that work, the LangChain-specific gotchas, and what we'd build differently next time.
We run a fleet of LLM agents on Kubernetes. They're stateful, bursty, and expensive — none of which K8s defaults are good at. Here's what we changed.
I fine-tuned Llama 3 8B on a single 4090 over a weekend for a side project. Here's what worked, what cost more than expected, and what I'd do differently.
