InfoQ Homepage AI, ML & Data Engineering Content on InfoQ
-
/articles/effective-practices-ai-chat-based-coding/en/smallimage/effective-practices-ai-chat-based-coding-thumbnail-1751458791140.jpg)
Effective Practices for Coding with a Chat-Based AI
In this article, we explore how AI agents are reshaping software development and the impact they have on a developer’s workflow. We introduce a practical approach to staying in control while working with these tools by adopting key best practices from the discipline of software architecture, including defining an implementation plan, splitting tasks, and so on.
-
/articles/docker-size-dive/en/smallimage/docker-size-dive-thumbnail-1751012053381.jpg)
Why Is My Docker Image So Big? A Deep Dive with ‘dive’ to Find the Bloat
AI images typically bloat from massive library installations and base OS components, with large Docker images slowing AI development and increasing costs. Chirag Agrawal demonstrates how to diagnose bloat using Docker's history and the interactive 'dive' tool to examine each layer in detail. The article shows how effective diagnosis leads to targeted optimizations.
-
/articles/state-space-solution-to-hallucinations-state-space-models/en/smallimage/state-space-solution-to-hallucinations-state-space-models-thumbnail-1750675024772.jpg)
The State Space Solution to Hallucinations: How State Space Models are Slicing the Competition
AI-powered search tools often hallucinate and make up facts, misquote sources, and recycle outdated information. The real cause of this is tied to the architecture of most AI models: Transformer. In this article, author Albert Lie explains why transformers struggle with hallucinations, how State Space Models (SSMs) offer a solution, and what this shift could mean for the future of AI search.
-
/articles/spotting-image-differences-visual-software-testing-ai/en/smallimage/spotting-image-differences-visual-software-testing-ai-thumbnail-1749461791635.jpg)
Spotting Image Differences in Visual Software Testing with AI
Current AI, including multimodal models, fails at robust visual regression testing, missing structural changes that pixel-based tools flag as false positives. This article proposes a CNN-based solution to compare image segments, tolerating minor displacements. For larger distortions, a multi-scale algorithm realigns the images before comparison, isolating the true differences.
-
/articles/AI-legacy-modernization/en/smallimage/AI-legacy-modernization-thumbnail-1746528855677.jpg)
AI Interventions to Reduce Cycle Time in Legacy Modernization
In this article, we share our experiences and insights on how large language models (LLMs) helped us uncover and enhance the conceptual constructs behind software. We discuss how these approaches address the inherent complexity of software engineering and improve the likelihood of success in large, complex software modernization projects.
-
/articles/practical-design-patterns-modern-ai-systems/en/smallimage/practical-design-patterns-modern-ai-systems-thumbnail-1747122253617.jpg)
Beyond the Gang of Four: Practical Design Patterns for Modern AI Systems
In this article, author Rahul Suresh discusses emerging AI patterns in the areas of prompting, responsible AI, user experience, AI-Ops, and optimization, with code examples for each design pattern.
-
/articles/lcm-paradigm-shift-ai-reasoning/en/smallimage/lcm-paradigm-shift-ai-reasoning-thumbanil-1747043782723.jpg)
Large Concept Models: a Paradigm Shift in AI Reasoning
Differently from LLMs, Large Concept Models (LCMs) use structured knowledge to grasp relationships between concepts, enhancing the decision-making process and providing a transparent reasoning audit trail. Using LCMs with LLMs can facilitate building AI systems that can analyze complex scenarios and effectively communicate insights, driving towards developing more reliable and explainable AI.
-
/articles/best-practices-energy-efficient-ai-ml-systems/en/smallimage/best-practices-energy-efficient-ai-ml-systems-thumbnail-1746711047911.jpg)
Best Practices to Build Energy-Efficient AI/ML Systems
In this article, author Lakshmithejaswi Narasannagari discusses the sustainable innovations in AI/ML technologies, how to track carbon footprint in all stages of ML systems lifecycle and best practices for model development and deployment.
-
/articles/domain-driven-rag/en/smallimage/domain-driven-rag-thumbnail-1746086725084.jpg)
Domain-Driven RAG: Building Accurate Enterprise Knowledge Systems through Distributed Ownership
Retrieval augmented generation (RAG) can help reduce LLM hallucination. Learn how applying high-quality metadata and distributing ownership of documents and prompts to domain experts can further increase accuracy in RAG applications. An additional layer of intelligence can use metadata to focus RAG searches on a specific domain for even better results.
-
/articles/ocr-ai-document-processing/en/smallimage/ocr-ai-document-processing-thumbnail-1745914250509.jpg)
Beyond OCR: How AI is Transforming Document Processing for Enterprise Applications
In this article, author Jitender Jain discusses AI driven document processing techniques for an intelligent, adaptive approach to document processing, to interpret documents in context and not just by visual structure.
-
/articles/distributed-cloud-privacy-ai/en/smallimage/Distributed-Cloud-Computing-Enhancing-Privacy-with-AI-Driven-Solutions-thumbnail-1745331120613.jpg)
Distributed Cloud Computing: Enhancing Privacy with AI-Driven Solutions
Distributed cloud, PETs, and AI enable secure, private data processing. This integration enhances collaboration, security, and compliance across marketing, finance, and healthcare, addressing the growing need for data protection.
-
/articles/shadow-table-strategy-data-migration/en/smallimage/Shadow-Table-Strategy-for-Seamless-Service-Extractions-and-Data Migrations-thumbnail-1744019310168.jpg)
Shadow Table Strategy for Seamless Service Extractions and Data Migrations
The shadow table strategy creates a synchronized duplicate of the data that keeps the production system fully operational during changes, enabling zero-downtime migrations. The approach supports diverse scenarios - including database migrations, microservices extractions, and incremental schema refactoring - that update live systems safely and progressively.