AWS Strands Labs Releases Strands Decider 2B: An Open Source Decision Model That Picks Options in About 115 ms
AWS Strands Labs releases Strands Decider 2B, an open source decision model. It does not generate text. It reads a state and typed questions, then returns a choice, a yes/no probability, or a score with a calibrated confidence. The model has 1.9 billion parameters and runs locally on a CPU, a consumer GPU, or an Apple silicon Mac. Is it deployable? Yes, for local and self-hosted use. Weights are on Hugging Face under Apache-2.0, and pip install strands-decider gives a CLI and an HTTP server.
Get smart on it
A decision model is a type of AI that picks between options or rates them on a scale, rather than generating text like traditional language models. AWS Strands Labs released an open-source decision model with 1.9 billion parameters that answers three types of questions: choosing one option from multiple choices, providing yes/no probabilities, or scoring on an ordered rubric. The model runs locally on standard hardware and completes requests in about 115 milliseconds, making it suitable for tasks like routing decisions, tool selection, and guardrails in AI systems. This represents a new category of models designed to constrain AI outputs to specific decision types rather than allowing arbitrary text generation.
Related news
Open-sourcing AstaBrief, the fast report-generation model in Asta
Making enterprise reporting tools openly available could democratize access to automation that typically requires expensive proprietary software licenses.
A Coding Guide to Google Research’s Kauldron: Configs That Are Plain Data, Components Wired by String, and a JAX Trainer You Can Read End to End
In this tutorial, we implement Kauldron, the JAX training library from Google Research that describes itself as optimized for research velocity and modularity, and we take those two words literally by testing what they actually buy us. We install it, then spend the first half of the notebook on the three mechanisms that make Kauldron different from a stack of Flax and Optax: konfig, which turns an experiment into a tree of plain dictionaries that round-trip through JSON; kontext, which wires co
