Modern alignment: DPO, KTO, ORPO and SimPO — the sommelier who learns without a reward modelMay 27, 2026
MLOps specific to LLMs in 2026: the landscape of three modalities, six stages and ten tools that make them workMay 21, 2026
eBPF in local inference and statistical drift detection: closing the LLM observability loop in 2026May 20, 2026
MCP from the inside and its deep observability: the LSP of AI agents and how to see everything with OpenTelemetryMay 20, 2026
AgentSight and the new LLM tracing: zero-instrumentation with eBPF against Langfuse, LangSmith, Phoenix and companyMay 19, 2026
LLM inference operators on Kubernetes: OME, vLLM Production Stack, NVIDIA Dynamo and llm-dMay 18, 2026