Ever since we launched Query Assistant last June, we’ve learned a lot about working with—and improving—Large Language Models (LLMs) in production with Honeycomb. Today, we’re sharing those techniques so that you can use them to achieve better outputs from your own LLM applications. The techniques in this blog are a new Honeycomb use case. You can use them today. For free. With Honeycomb.
In today's dynamic world of technology and innovation, building products that resonate with customers and stand the test of time is no easy feat. At Almaden, we've cultivated a unique, Customer-Centric Product Design, approach to product development that prioritizes the customer's perspective over mere technological prowess. In this blog post, we'll delve into the core principles that drive our product development process, emphasizing the importance of understanding objectives, agile methodologies, and the modern tools we use to bring our ideas to life.
This tutorial guides you on how to use the Amazon SageMaker Orb to orchestrate model deployment to endpoints across different environments. It also shows how to use the CircleCI platform to monitor and manage promotions and rollbacks. It will use an example project repository to walk you through every step, from training a new model package version to deploying your model across multiple environments.
Top tips is a weekly column where we highlight what’s trending in the tech world today and list out ways to explore these trends. This week, we’re examining four use cases for AI in the ever-growing FinTech sector. The FinTech sector has transformed the discussion around the financial services industry from top to bottom.
Amazon Bedrock is a fully managed service that offers foundation models (FMs) built by leading AI companies, such as AI21 labs, Meta, and Amazon along with other tools for building generative AI applications. After enabling access to validation and training data stored in Amazon S3, customers can fine-tune their FMs to invoke tasks such as text generation, content creation, and chatbot Q&A—without provisioning or managing any infrastructure.
