Theme · 2 articles

Evaluation

Across learning, research, benchmarks and demos.

Agents LLM RAG Evaluation MLOps Classical ML Data Tooling Safety Policy

Learn · LLM

Decision models: what fits in one pass?

The new System 1 models promise fast, cheap decisions without a chain of thought. A small arithmetic test shows why that can be useful, where it can fail, and why the confidence score deserves a closer look.

V. Levy dit Vehel, PhD · 21 Oct · 8 min

Learn · RAG

Embeddings: similar in what way?

A vector search can give you a precise answer before you have decided what should count as a good one. A few shapes help explain the missing decision—and why embeddings are still enormously useful.

V. Levy dit Vehel, PhD · 5 Sept · 5 min