Introducing Serverless RL

Evaluating cost and hyperparameters for Pinecone RAG systems with W&B Weave

Make evaluations count: Comparing AI application evaluation results using W&B Weave

Product newsletter: Updates and new features for September 2025

AI Guardrails: Coherence scorers

DeepSeek-R1 vs OpenAI o1: A guide to reasoning model setup and evaluation

AI guardrails: Toxicity scorers

Building a best in class AI programmer with Weights & Biases Weave

AI guardrails: Bias scorers

Leveraging foundation models at financial institutions

AI scorers: Evaluating AI-generated text with BLEU

AI scorers: Evaluating AI-generated text with ROUGE

Financial risk management in the era of GenAI

New year, new tools: Unlocking AI in 2025 with Weights & Biases

Announcing our newest GenAI course—LLM Apps: Evaluation

A practical guide to the EU AI Act

Integrating W&B Weave With NVIDIA AI Blueprint for AI Virtual Assistants to Enhance AI Observability

AI guardrails: Understanding PII detection

Monitoring Amazon Bedrock Agents with W&B Weave

GraphRAG: Enhancing LLMs with knowledge graphs for superior retrieval

How to fine-tune a large language model (LLM)

Combining open-source PII redaction with closed-model analysis in healthcare using Llama 3.1, MedSpacy and GPT-4o

Securing your LLM applications against prompt injection attacks

W&B Weave newsletter: General availability, playground, guardrails, leaderboards, and more