All activity
W&B Training offers serverless reinforcement learning for post-training large language models to improve their reliability performing multi-turn, agentic tasks while also increasing speed and reducing costs.
W&B Training by Weights & BiasesThe fast and easy way to train AI agents with serverless RL
Dave Daviesleft a comment
Training reliable, multi-turn AI agents with reinforcement learning has always been complex, unstable, and expensive. W&B Training changes that. With serverless RL, ART (Agent Reinforcement Trainer), and RULER (Relative Universal LLM-Elicited Rewards), you can fine-tune large language models to become more capable and trustworthy without managing infrastructure or writing custom reward...
W&B Training by Weights & BiasesThe fast and easy way to train AI agents with serverless RL
Dave Daviesleft a comment
Accessing the best open-source models shouldn’t require juggling API keys, managing clusters, or signing up with multiple providers. W&B Inference, powered by CoreWeave, gives AI engineers instant access to top foundation models - including DeepSeek, Qwen3, Kimi K2, Llama 4, Phi, and OpenAI GPT OSS - directly within the Weights & Biases platform. With Inference, you can: - Call open-source LLMs...
W&B Inference by Weights & BiasesAccess to top open-source LLMs
W&B Inference, powered by CoreWeave, provides API and playground access to leading open-source LLMs, enabling Weights & Biases users to develop AI applications and agents without needing to sign up with a hosting provider or host models themselves.
W&B Inference by Weights & BiasesAccess to top open-source LLMs
W&B Weave is a lightweight tool, from Weights & Biases, to help AI engineers evaluate, monitor, and iterate on agentic AI applications.
W&B Weave by Weights & BiasesEvaluate, monitor, and iterate on AI agents
W&B Experiments lets you quickly and easily implement experiment logging by adding just a few lines to your script and start logging results. Our lightweight integration works with any Python script.
W&B ExperimentsThe system of record for your model training
Dave Daviesleft a comment
Building demos of AI agents is deceptively easy, but getting them into production is not. Weave helps AI engineers build AI agents with confidence. With just one line of code (weave.init("quickstart")), you can trace any LLM-powered application to gain full visibility into your agentic workflows. Weave is integrated with leading AI frameworks, LLMs, and protocols. With Weave you can: -...
W&B Weave by Weights & BiasesEvaluate, monitor, and iterate on AI agents