Passion for Technology
Two years after living with AI assistants in the editor, habits have settled. A reflection on what’s changed in day-to-day coding, what has been learned, and what remained to be discovered.
Read more
Three years after RLHF became popular, the alignment landscape is richer. A review of RLHF, DPO, and recent methods like KTO or ORPO, with criteria for choosing.
Read more
SLSA has been in its 1.0 version for a year and a half, and the ecosystem has had time to adopt it. A review of what works, what still hurts, and where it makes sense to start.
Read more
Measuring RAG system quality is more subtle than it seems. Metrics, golden sets, and the most common evaluation mistakes.
Read more
Software consumes energy. Reducing its carbon footprint isn’t just virtue — it’s operational savings. Eight practical principles applicable from tomorrow.
Read more
LLM apps need specific observability: prompt/response traces, token costs, quality metrics. 2024 tools and patterns.
Read more
Kubecost gives cost visibility by namespace/deployment/label. OpenCost is its OSS core. When it helps and how to integrate.
Read more
Misconfiguring Alertmanager is the norm. Sensible routing, silencing, grouping, and on-call rotation patterns to prevent alert fatigue.
Read more
Chaos engineering is more than ‘break production’. How to implement with hypotheses, controlled blast radius, and measurable ROI.
Read more
Ansible orchestrates servers, Pulumi manages cloud infra with real code. They’re complementary, not competitors. How to combine without duplicating.
Read more