GitHub - Contextualist/lone-arena: Self-hosted LLM chatbot arena, with yourself as the only judge

Self-hosted LLM chatbot arena, with yourself as the only judge - GitHub - Contextualist/lone-arena: Self-hosted LLM chatbot arena, with yourself as the only judge

GitHub - uptrain-ai/uptrain: Your open-source LLM evaluation toolkit. Get scores for factual accuracy, context retrieval quality, tonality, and many more to understand the quality of your LLM applications

Your open-source LLM evaluation toolkit. Get scores for factual accuracy, context retrieval quality, tonality, and many more to understand the quality of your LLM applications - GitHub - uptrain-ai...

The pain points of building a copilot

We investigated the process and pain points of building a copilot.

Top Evaluation Metrics for RAG Failures

Troubleshoot LLMs and Retrieval Augmented Generation with Retrieval and Response Metrics

SPADE: Synthesizing Assertions for Large Language Model Pipelines

Operationalizing large language models (LLMs) for custom, repetitive data pipelines is challenging, particularly due to their unpredictable and potentially catastrophic failures. Acknowledging the inevitability of these errors, we focus on...

Should the patient really get the drug?

In this article I discuss why doctors are so poor at weighing benefits vs harms of drugs, why this causes them to prescribe far too much, and what do about it.