Creating a SaaS Platform on Google Kubernetes Engine
Learn about the fundamentals of building a SaaS platform on Google Kubernetes Engine (GKE) and explore popular SaaS GKE architectures and storage options.
Cloud CISO Perspectives: Why ISACs are valuable security partners
Learn why ISACs are valuable security partners for Google Cloud and the industry in this Cloud CISO Perspectives blogpost.
Build a foundation model (FM) powered customer service bot with agents for Amazon Bedrock
Build a foundation model (FM) powered customer service bot with agents for Amazon Bedrock
Retrieval-Augmented Generation with LangChain, Amazon SageMaker JumpStart, and MongoDB Atlas semantic search
Learn how to harness the power of retrieval-augmented generation using LangChain and Amazon SageMaker JumpStart, and leverage MongoDB Atlas semantic search for domain-specific tasks.
Moderate your Amazon IVS live stream using Amazon Rekognition
Moderate Amazon IVS live stream using Amazon Rekognition with automated content moderation and human-in-the-loop review.
How I Fly
Host and scale your applications close to your users with ease using Fly.io
Cybersecurity Lakehouses Best Practices Part 4: Data Normalization Strategies
Explore the importance of data normalization strategies for building a Cybersecurity Lakehouse and learn how to overcome challenges in this final part of the 'Cybersecurity Lakehouses Best Practices' blog series.
Enterprise LLM challenges and how to overcome them
Challenges and solutions for utilizing enterprise-grade large language models (LLMs) in AI applications
Enterprise LLM challenges and how to overcome them
Addressing enterprise challenges with large language models (LLMs) in AI through data-centric development, with a focus on customization and accuracy.
How to Scale Your EMA
Learn how to optimize the scaling of your EMA model for improved training dynamics and performance in machine learning.
Automating Behavioral Testing in Machine Translation
Automating Behavioral Testing in Machine Translation: Proposing a practical evaluation framework using Large Language Models (LLMs) to generate source sentences and verify behavior of MT systems.
ReLU Strikes Back: Exploiting Activation Sparsity in Large Language Models
Exploiting activation sparsity in large language models to reduce computation and weight transfer, using ReLU activations with minimal performance trade-offs.