Qualiteg - Generative AI Frontlines - Qualiteg Journal (Page 2)

LLM

KV Cache Offloading Strategies and a Practical Understanding of GQA

Hello! Welcome to a special extra installment of our LLM Inference Infrastructure Provisioning Course! Part 3, "Estimating Inference-Time Memory Consumption for Your Model", we introduced the two major consumers of GPU memory, the model footprint and the KV cache, and explained how to calculate the KV cache size

Daily Dev Tips

Unstable Multi-Turn Image Editing 🍌 with Google GenAI SDK Streaming: the Problem and the Fix

Hello! While implementing multi-turn image editing with Gemini 3 Pro Image (Nano Banana Pro), we ran into a troublesome problem: it worked sometimes and failed other times. In this article, we share the symptoms, the investigation process, and the solution. The Symptoms Environment Google GenAI SDK library (pip): google-genai 1.

LLM

The Reality of LLM Training: From GPU Selection to Training Costs

Hello! Why can OpenAI and Anthropic build world-class LLMs while no LLM from Japan stands shoulder to shoulder with them? Is it a gap in technical capability? A talent problem? The answer is simpler than that: the number of GPUs, and money. Today we focus on "LLM training"

Generative AI Frontlines

Getting Started with Claude Code

Hello! Today we take up Claude Code, the AI coding agent that has been generating a lot of buzz among engineers lately. AI coding assistants have multiplied rapidly over the past year or two, and many of you probably feel you can no longer tell which one to choose. In

AI Agents

The State and Future of Coding Agents, Part 1: The Landscape and Fundamentals

Hello! This time, we present a grand tour of the more than 20 flourishing AI coding tools out there—introduced and explained all in one go! AI-assisted coding is by now simply how things are done, and new tools appear at a dizzying pace. We use several tools in our

Blog

Will Engineering Become a "Hobby"?

Hello! Today I would like to reflect on vibe coding (that is, having AI build software for you automatically) and the future of us engineers. For the record, I have not reached any binary conclusion about whether we should build things ourselves or leave it all to AI through vibe

Generative AI Frontlines

How to Build AI Lipsync, Part 5 (Second Half): Implementing Transformers and Making Practical Technology Choices

Why can't the Transformer that powers GPT simply be dropped into lipsync? We unpack three challenges — data, computation, and overfitting — how to choose between LSTMs and Transformers in practice, and transfer learning as a third option, in a dialogue between Professor Quo and Manabu.

Generative AI Frontlines

The Dawn of the Disposable Software Era — A Fundamental Transformation of Market Structure and Japanese Companies

Hello — this is the consulting division of Qualiteg Inc. The rapid evolution of generative AI is fundamentally reshaping how software is built. In 2024, large language models such as Claude, GPT-4, and Gemini dramatically improved their code generation capabilities, and development tools like GitHub Copilot, Cursor, and Windsurf came into

Generative AI Frontlines

What Are "Guardian Agents," the New Sentinels of the AI Agent Era?

Hello! Today we take a closer look at Guardian Agents, a concept Gartner recently announced. Gartner's Official Definition In June 2025, Gartner—well known for its Hype Cycle—published its perspective on Guardian Agents.Guardian agents are AI-based technologies designed to support safe and trusted interactions with AI—