Build Agentic Workflows with OpenAI GPT OSS on Amazon SageMaker AI and Amazon Bedrock AgentCore

Favorite OpenAI has released two open-weight models, gpt-oss-120b (117 billion parameters) and gpt-oss-20b (21 billion parameters), both built with a Mixture of Experts (MoE) design and a 128K context window. These models are the leading open source models, according to Artificial Analysis benchmarks, and excel at reasoning and agentic workflows.

Read More
Shared by AWS Machine Learning September 18, 2025

Supercharge your organization’s productivity with the Amazon Q Business browser extension

Favorite Generative AI solutions like Amazon Q Business are transforming the way employees work. Organizations in every industry are embracing these tools to help their workforce extract valuable insights from increasingly fragmented data to accelerate decision-making processes. However, the adoption of generative AI tools hasn’t been without its challenges. Two

Read More
Shared by AWS Machine Learning September 18, 2025

Unified multimodal access layer for Quora’s Poe using Amazon Bedrock

Favorite Organizations gain competitive advantage by deploying and integrating new generative AI models quickly through Generative AI Gateway architectures. This unified interface approach simplifies access to multiple foundation models (FMs), addressing a critical challenge: the proliferation of specialized AI models, each with unique capabilities, API specifications, and operational requirements. Rather

Read More
Shared by AWS Machine Learning September 17, 2025

Schedule topology-aware workloads using Amazon SageMaker HyperPod task governance

Favorite Today, we are excited to announce a new capability of Amazon SageMaker HyperPod task governance to help you optimize training efficiency and network latency of your AI workloads. SageMaker HyperPod task governance streamlines resource allocation and facilitates efficient compute resource utilization across teams and projects on Amazon Elastic Kubernetes

Read More
Shared by AWS Machine Learning September 16, 2025

Migrate from Anthropic’s Claude 3.5 Sonnet to Claude 4 Sonnet on Amazon Bedrock

Favorite This post is co-written with Gareth Jones from Anthropic. Anthropic’s Claude 4 Sonnet model has launched on Amazon Bedrock, marking a significant advancement in foundation model capabilities. Consequently, the deprecation timeline for Anthropic’s Claude 3.5 Sonnet (v1 and v2) was announced. This evolution creates a dual imperative for production

Read More
Shared by AWS Machine Learning September 13, 2025

Unlock model insights with log probability support for Amazon Bedrock Custom Model Import

Favorite You can use Amazon Bedrock Custom Model Import to seamlessly integrate your customized models—such as Llama, Mistral, and Qwen—that you have fine-tuned elsewhere into Amazon Bedrock. The experience is completely serverless, minimizing infrastructure management while providing your imported models with the same unified API access as native Amazon Bedrock

Read More
Shared by AWS Machine Learning September 13, 2025

Automate advanced agentic RAG pipeline with Amazon SageMaker AI

Favorite Retrieval Augmented Generation (RAG) is a fundamental approach for building advanced generative AI applications that connect large language models (LLMs) to enterprise knowledge. However, crafting a reliable RAG pipeline is rarely a one-shot process. Teams often need to test dozens of configurations (varying chunking strategies, embedding models, retrieval techniques,

Read More
Shared by AWS Machine Learning September 13, 2025