Sara Wiltberger

Sara Wiltberger

Google LabsGoogle Labs
PM at DeepMind
16 points
All activity
Stax is a tool from Google Labs to solve LLM evaluation. Move beyond "vibe testing" by building custom autoraters to measure what matters to you. It's a full toolkit for testing your AI stack with your data, with support for all major model providers.
Stax
StaxMove your LLM evals from vibes to data
Sara Wiltbergerleft a comment
Fantastic team and looks like a great product. Can't wait to try it out
Common Room
Common RoomThe intelligent community growth platform - start for free