Week 6, year 2025

• What's Cooking Inside AxonIQ's Kitchen - Our 2025 Outlook - AxonIQ isn’t here to play by the old rules—we’re here to rewrite them. Welcome to the latest deep dive into our world of making event sourcing easy, where we challenge assumptions and push boundaries with Axon Framework, Axon Server, and the radical shift that is Dynamic Consistency Boundaries (DCB). [AxonIQ Blog]
• Retrieval Augmented Generation (RAG) - A pre-trained GenAI model lacks recent and specific information about a domain. Bharani Subramaniam and I explain how Retrieval Augmented Generation (RAG) can fill that gap. [Martin Fowler]
• Panel at goto Copenhagen: "Where is SW development Going - was on a panel at goto Copenhagen last September with Holly Cummings, Trisha Gee, Dave Farley, and Daniel Terhorst-North. We discussed the current state of software development and where it was heading. Given the timing, there was much discussion about the role AI would play in our profession's future. [Martin Fowler]
• GenAI Patterns: RAG Limitations and Hybrid Retriever - Today Bharani Subramaniam and I outline four limitations to the simple RAG from yesterday, and the pattern that addresses the first of these: Hybrid Retriever. This tackles the inefficiencies of embeddings-based search by combining it with other search techniques. [Martin Fowler]
• GenAI Patterns: Retrieval Augmented Generation (RAG) - A pre-trained GenAI model lacks recent and specific information about a domain. Bharani Subramaniam and I explain how Retrieval Augmented Generation (RAG) can fill that gap. [Martin Fowler]
• The DeepSeek Series: A Technical Overview - The appearance of DeepSeek Large-Language Models has caused a lot of discussion and angst since their latest versions appeared at the beginning of 2025. But much of the value of DeepSeek's work comes from the papers they have published over the last year. Shayan Mohanty provides an overview of these papers, highlighting three main arcs in this research: a focus on improving cost and memory efficiency, the use of HPC Co-Design to train large models on limited hardware, and the development of emergent reasoning from large-scale reinforcement learning [Martin Fowler]

Permalink | From 03 February 2025 to 09 February 2025 | Last updated on: Thu, 6 Feb 2025 15:19:29 GMT