Product newsletter: Updates and new features for November 2025

Migrate from Neptune to Weights & Biases

Weights & Biases gets a new terminal UI

Evaluating LLMs on Amazon Bedrock

AWS partnership year in review 2024

Working with Pixtral Large for visual chart understanding

Automated medical note generation: Fine-tuning GPT models for clinical documentation using Azure OpenAI and Weights & Biases

Using version tags and artifacts to organize your most valuable ML assets

LLM Evaluation on Google Vertex AI

How to train an LLM router with W&B Weave and Not Diamond

Build a reliable GenAI search system with Gemini Grounding and Vertex AI

Building and evaluating a RAG system with DSPy and W&B Weave

Ensembling and ensemble learning methods

Hacking a skeleton to detect kids costumes and greet them with a custom spooky message

Product newsletter: Updates and new features from October

Getting started with Apple MLX

Monitoring trustworthy agents with Vijil and Weave

Building an LLM Python debugger agent with the new Claude 3.5 Sonnet

How to evaluate a Langchain RAG system with RAGAs

Announcing: More TPU metrics in W&B Models

Weave newsletter: Multimodal LLMs, RAG tutorial, and OpenAI DevDay

Building reliable apps with GPT-4o and structured outputs

PHI and PII for healthcare in the world of AI