-
In this post, we show how to build a generative AI solution using Amazon Bedrock that creates bespoke holiday packages by combining customer profiles and preferences with real-time pricing data. We demonstrate how to use Amazon Bedrock Knowledge Bases for travel information, Amazon Bedrock Agents for real-time flight …
Read More -
In this post, we show how to create an AI-powered call center agent for a fictional company called AnyTelco. The agent, named Telly, can handle customer inquiries about plans and services while accessing real-time customer data using custom tools implemented with the Model Context Protocol (MCP) framework. Link to …
Read More -
This post explores how to implement a robust monitoring solution for multi-tenant AI deployments using a feature of Amazon Bedrock called application inference profiles. We demonstrate how to create a system that enables granular usage tracking, accurate cost allocation, and dynamic resource management across complex …
Read More -
The image processing folks added specialized AVX2 versions of their code, but found that it was crashing with an illegal instruction exception. The code went something like this: void SwizzleAVX2(uint32_t* source, uint32_t* destination, uint32_t count) { ⟦ do stuff using AVX-only instructions ⟧ ⟦ such as _mm256_cv Link …
Read More -
The Beta version of IntelliJ IDEA 2025.2 is now available, marking the end of our Early Access Program for this release cycle. Download IntelliJ IDEA 2025.2 Beta Thank you to everyone who used the EAP builds, shared feedback, and helped shape this release. As we mentioned in the EAP opening post, we have moved away […] …
Read More -
Starting from 2025.2, the default terminal implementation is now the reworked terminal. To create this new implementation, the classic terminal was rewritten almost from scratch to provide the technical foundation for new terminal features like visual separation of executed commands, AI integration, and the ability to …
Read More -
Introduction In a recent engagement, our team of Data Scientists and Software Engineers, developed a series of custom AI models to meet our customer's specific use case. While doing so, consideration was given to how best to allow Data Scientists the freedom to quickly experiment and iterate on model development, while …
Read More -
OpenAI is launching an initial $50 million fund that supports nonprofit and community organizations, informed by the independent OpenAI Nonprofit Commission report. Link to article: https://openai.com/index/50-million-fund-to-build-with-communities
Read More -
Evaluating the performance of large language models (LLMs) goes beyond statistical metrics like perplexity or bilingual evaluation understudy (BLEU) scores. For most real-world generative AI scenarios, it’s crucial to understand whether a model is producing better outputs than a baseline or an earlier iteration. This …
Read More -
In this post, we demonstrate how to integrate Amazon S3 Vectors with Amazon Bedrock Knowledge Bases for RAG applications. You'll learn a practical approach to scale your knowledge bases to handle millions of documents while maintaining retrieval quality and using S3 Vectors cost-effective storage. Link to article: …
Read More -
In this post, we walk through the custom model on-demand deployment workflow for Amazon Bedrock and provide step-by-step implementation guides using both the AWS Management Console and APIs or AWS SDKs. We also discuss best practices and considerations for deploying customized Amazon Nova models on Amazon Bedrock. Link …
Read More -
The new t-shirt designs celebrate seasoned software engineers surviving industry challenges like Y2K and IE6. The Vintage Tech Emblem Tee and Embroidered Patch Edition embody resilience and experience, emphasizing their importance in producing reliable code. These shirts serve as a declaration of enduring value in a …
Read More -
When building applications that interact with databases, developers frequently encounter scenarios where default SDK configurations don't align with their specific operational requirements. They need to customize SDK behavior to address real-world challenges like network instability, performance bottlenecks, debugging …
Read More -
The Ktor 3.2.2 patch release brings a critical fix for Android D8 compatibility, along with some minor enhancements and bug fixes. 🚀 Get started Ready to explore Ktor 3.2.2? Start building your next project today with our interactive project generator at start.ktor.io. Your feedback and contributions are always …
Read More -
The Windows Runtime provides a class named PropertyValue which is a helper class for boxing non-inspectables. "Boxing" means taking a value type and wrapping inside an object so it can be used as an object type, and in the Windows Runtime, "objects" are represented by the IInspectable interface. …
Read More -
Intro Local development can be challenging when apps rely on external services like databases or queues, leading to brittle scripts and inconsistent environments. Fiber v3 and Testcontainers solve this by making real service dependencies part of your app’s lifecycle, fully managed, reproducible, and developer-friendly. …
Read More -
At JetBrains, we care about Kotlin compiler quality. One powerful way to test it? Fuzzing, an approach that feeds programs unexpected, often random, inputs to uncover bugs that traditional tests may miss. It may sound chaotic, but it works, especially for complex software like compilers. In a previous post, our …
Read More -
Organizations are adopting large language models (LLMs), such as DeepSeek R1, to transform business processes, enhance customer experiences, and drive innovation at unprecedented speed. However, standalone LLMs have key limitations such as hallucinations, outdated knowledge, and no access to proprietary data. Retrieval …
Read More -
Onboarding development teams with new tools can be difficult. People disagree about what’s best, and different organizations have different pains, needs, and regulations. Which option is the best for you? How do you find consensus in your team? How much control do you need over your data? There are many considerations, …
Read More -
We are excited to announce the next step for IntelliJ IDEA: we are moving to a single, unified distribution. And yes, before you ask, our commitment to open source remains as strong as ever. There will be just one IntelliJ IDEA installer, replacing the separate downloads for Community Edition and Ultimate Edition. In …
Read More