PinnedPrompt Evaluation: Systematically testing and improving your Gen AI prompts at scale.One of the best ways to differentiate between a gen AI science project and a viable product is to count the number of automated tests.Apr 11Apr 11
How to deploy a secure instance of Anthropic Computer Use on AWSA simple walkthrough with examples3d ago3d ago
Prompt DecompositionHow adding more calls to an LLM can unlock scale and increase accuracy while lowering both cost and latency.Jun 1710Jun 1710
Goodbye Hallucinations, Hello AttributionsHow to build confidence in Generative AI by detecting everything except hallucinations.Jan 30Jan 30
Published inBetter ProgrammingHow to Deploy Stable Diffusion Model on Amazon SageMakerMeet the open source AI that is transforming the worlds of video editing, gaming, art, music, and more!Oct 24, 20221Oct 24, 20221