Langfuse vs. LangSmith II: Datasets and Evaluation.

Langfuse vs Langsmith I: Prompt Versioning and Tracing.

What prompt hacking is and how to avoid it.

LLMs do not kill other LLMs... or do they?

I have a classical philology degree from the Autonomous University of Madrid and work as a computational linguist at Paradigma. Before that, I worked as a computational linguist at Molino de Ideas, Bitext and Google in, among others, lexical richness analysis, sentiment analysis and conversational system projects. I have co-organised data science and natural language processing communities such as R-Ladies and Lingwars.
linkedin twitter github