GenAI and LLMs development, trends and implications (17. - 23.2.2025)

Releases:

OpenAI cancels o3 release and announces roadmap for GPT 4.5, 5

OpenAI releases operator, an AI agent for web-based tasks

OmniHuman-1 released - AI-generated human animation

Latin America launches Latam-GPT to improve AI cultural relevance

Vision and video generation:

Top 3 video generation models

Step-by-step reasoning can fix madman logic in vision AI

In software development:

Prompt engineering: Is it a new programming language?

What role does LLM reasoning play for software tasks?

How do LLMs benefit developer productivity?

How a software architect uses Artificial Intelligence in his daily work

How to debug code with GitHub Copilot

Free ebook: Coding with ChatGPT and Other LLMs

OpenAI vs. DeepSeek: Which AI understands Kotlin better?

Zero human code: What I learned from forcing AI to build (and fix) its own code for 27 straight days

And software testing:
Meta introduces LLM-powered tool for software testing
TDD and generative AI – a perfect pairing?
Generate unit tests with AI using Ollama and Spring Boot

Building apps:
Emerging patterns in building GenAI products - Guardrails
Build scalable GenAI applications in the cloud: From data preparation to deployment
Building intelligent microservices with Go and AWS AI services
Spring AI with Anthropic’s Claude models example

LLMs:
How LLMs work: Pre-training to post-training, neural networks, hallucinations, and inference
Dive into tokenization, attention, and key-value caching
The Delegated Chain of Thought architecture
A comprehensive guide to Generative AI training
Semantic clustering of user messages with LLM prompts - tutorial

LLMs and search:
Have LLMs solved the search problem?
Search: From basic document retrieval to answer generation

RAG:
Building a simple RAG application with Java and Quarkus
Creating an agentic RAG for Text-to-SQL applications
Multimodal RAG with Colpali, Milvus, and VLMs
Retrieval Augmented Generation in SQLite

Agents:
AI agents from zero to hero – part 1
Agentic workflows for unlocking user engagement insights
Azure AI Agent Service now in public preview for developers in AI Foundry SDK and Portal
Observability and DevTool platforms for AI agents
AI Agents: Future of automation or overhyped buzzword?

Future:
40% of AI data breaches will arise from cross-border GenAI misuse by 2027

GenAI and LLMs development, trends and implications (20. - 26.1.2025)

What’s the real ROI of AI in 2025?

Google releases experimental AI reasoning model - Gemini 2.0 Flash Thinking Experimental

DeepSeek open-sources DeepSeek-V3, a 671B parameter mixture of experts LLM

Nvidia Ingest aims to make it easier to extract structured information from documents

Microsoft Research unveils rStar-Math, advancing mathematical reasoning in Small Language Models

Microsoft Phi-4 is a Small Language Model specialized for complex math reasoning

Amazon Bedrock introduces Multi-Agent Systems (MAS) with open-source framework Integration

Luma AI’s Ray2 video model is now available in Amazon Bedrock

Want to integrate AI into your business? Fine-tuning won’t cut it

Why generative AI apps’ quality often sucks and what to do about it

Building successful AI Apps: The dos and don’ts

Agentic Mesh: Towards enterprise-grade agents

What OpenAI's reasoning models mean for GPT and AI

Advancing AI reasoning: Meta-CoT and system 2 thinking

Choose a database with a hybrid vector search for AI apps

A framework for building micro metrics for LLM system evaluation

Why LLMs suck at ASCII art
Large Language Models: A short introduction

Human minds vs. machine learning models - exploring the parallels and differences between psychology and machine learning
Understanding emergent capabilities in LLMs - lessons from biological systems

Chain-of-Thought Prompting - a comprehensive analysis of reasoning techniques in Large Language Models

RAG isn’t immune to LLM hallucination

Designing, building & deploying an AI chat app from scratch - part 1 and part 2
A guide to deploying AI for real-time content moderation
Real-time data streaming with AI

How LLMs are going to change code generation in modern IDEs
Meet Junie, your coding agent by JetBrains
"Fix with AI" button to automate Playwright test fixes
Collaborative Intelligence - maximizing human-AI partnerships in the workplace

Building effective agents with Spring AI (Part 1)
Fresh data for AI with Spring AI function calls
Powering LLMs with Apache Camel and LangChain4j

GenAI and LLMs development, trends and implications (13. - 19.1.2025)

Prompt engineering has become an essential skill for working effectively with large language models (LLMs) - guide on the best prompt engineering books

Google unveiled PaLiGeMMA 2 - a family of vision-language models (VLM)

NVIDIA’s announces DIGITS - its first personal AI computer

Projects like AYA Expanse are exploring multilingual capabilities

Combining local and cloud models to build a multimodal AI assistant answering complex image questions, with the option to run everything locally

Building deterministic GenAI chatbots in regulated industries

Importance of robust system memory as a key to personalized AI intelligence

Building reliable AI applications - LLM routing

Microsoft's framework for AI-driven cloud operations - AIOpsLab

Introducing Google's Vertex AI RAG engine

Enterprise RAG in Amazon Bedrock - learn details of Amazon Bedrock KnowledgeBases capability

Guide to using Snowflake Cortex for GenAI

Real-world applications and best practices using Azure AI and GPT-4

Developing an AI-powered smart guide for business planning & entrepreneurship

An experiment on integrating LLM into a console application

Comparing: Apache OpenNLP vs Stanford NLP for NLP

Supercharging RAG with MAS (Multi-Agent System)

How AI agents answer questions using domain knowledge

The rise of reasoner models - scaling test-time compute

Advancing complex medical reasoning with HuatuoGPT-o1

Creating artificial doubt significantly improves AI math accuracy

Major LLMs have the capability to pursue hidden goals

And the future:

AI adoption in 40% of power and utilities control rooms by 2027

Mobile app usage will decrease 25% due to AI assistants by 2027

From physics to AI: Why machine learning experts won the 2024 Nobel Prize & how to grasp LLMs with simple math

Why was the 2024 Physics Nobel Prize awarded to machine learning experts? And how does ML connect to physics? 

And how to understand LLMs from scratch using middle school mathematics?

GenAI and LLMs development, trends and implications (11. - 17.11.2024)

New models and functionality:

• Anthropic releases new Claude models and computer use feature
• Meta Releases NotebookLlama - Open-Source PDF to podcast toolkit

Building with LLMs:

• Leveraging various deployment options - Economics of hosting Open Source LLMs
• Efficient resource management with Small Language Models (SLMs) in Edge Computing
• A step-by-step guide - Building a reliable text classification pipeline with LLMs
• A local ChatGPT-like interface + Copilot in less than 10 minutes - using Ollama, Llama3, Continue, and Open WebUI
• Turn any document into a conversation-ready AI tool with open-source AnythingLLM
• AI image generation with OpenAI DALL·E 3 using Spring AI

Using models:

• Torch Compile - 2x faster Llama 3.2 with low effort
• Music transcription with multi-modal language models

RAG:

• How to implement a basic reranking system in RAG
• An introduction to Graph RAG
• Where does the magic of RAG go from?

LLMs generally:

• Can quantum computing help improve our ability to train large neural networks encoding LLMs?
• Inference with Gemma using Dataflow and vLLM

GenAI and LLMs development, trends and implications (7. - 13.10.2024)

Adoption:

• Bursting the Gen AI hype bubble - once and for all
• Basics - 10 critical AI concepts explained in 5 minutes
• Generally AI - Fantastic algorithms and where to find them
• Seven factors driving AI adoption
• Exploring the GenAI technology stack and how it all fits together
• Meta unveils Movie Gen, a new AI model for video generation

LLMs generally:

• Chain of Thought prompting for LLMs
• Operationalize a scalable AI with LLMOps principles and best practices
• Prompt Caching in LLMs: Intuition - how caching works in attention-based models
• Improving model quality without building larger models
• PayPal adds GenAI support with LLMs to its Cosmos.AI MLOps platform
• Fine-tuning Llama 3.2 for performance on targeted domains

New models and functionality:

• OpenAI Developer Day 2024 (SF) announces real-time API, vision fine-tuning, and more
• Meta releases Llama 3.2 with vision, voice, and open customizable models
• Claude AI - unboxing Anthropic’s LLM-based AI assistant, artifacts & use cases
• A Walkthrough of Nvidia’s latest multi-modal LLM family

AI agents:

• All about AI agents -  autonomy, reasoning, alignment, and more

AI-enhanced software development:

• Test-Driven Generation - adopting TDD with GenAI

Enhancing applications with GenAI:

• Latest innovations in recommendation systems with LLMs
• DocAI - chatting with AI and asking questions in the context of your documents

IT links (7. - 13.10.2024)

• Reducing memory footprint with Java Object Layout (JOL) library
• Object equality in Java - a degree of equality and fuzzy comparison

       Java Streams:

• Exploring findAny() and anyMatch()
• Effective techniques for optimizing Java Streams - scenarios of when to use Streams, and when to avoid them

• Mocking @Value in Spring Boot test
• Test-Driven Generation - adopting TDD with GenAI

• Multiple ways how to change field value before Update and Insert in Hibernate

• Secret management and rotation in AWS
• Microservice proliferation - too many microservices - the pitfalls associated with the excessive creation of microservices, insights on their causes, implications, and potential strategies for mitigation

• Data modeling and techniques and best practices for optimization in Snowflake
• Data Teams Survey - lag in DataOps and value delivered
• Setting up a Data Mesh organization
• Scaling Uber’s batch data platform - a journey to the cloud with Data Mesh principles