Daily Dev Tips
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
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
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
LLM
⚠️ A newer version of this article is available The latest LLM ranking (March 2026 edition) is here Read the latest LLM ranking (March 2026 edition) → Introduction This report is a comprehensive analysis of the performance of Japanese-capable LLMs, based on benchmark data from Nejumi Leaderboard 4 (the 2025/12/18
Daily Dev Tips
Hello! In this post, we walk through an important npm update that rolled out on December 9, 2025. On December 9, 2025, npm completely disabled classic tokens as part of a security hardening effort. As a result, projects that use private packages may suddenly find that npm install fails. (Public
LLM
Hello! Today's topic is the Anthropic Python SDK, a convenient way to work with the Anthropic Claude API. A fairly significant change landed about two weeks ago, so let's walk through it. Introduction "Wait, client.count_tokens() stopped working..." You updated the Anthropic Python
Daily Dev Tips
Hello! Today we built a small tool. It is a tool for doing a quick little grep on your logs. Free, of course. chocoGrep – A Free Browser Tool for a Quick Little grep of Your LogschocoGrep runs entirely in your browser: paste or drop a log file and grep it
Daily Dev Tips
Hello! When designing parallel processing systems that use multiple GPUs, it is easy to design the whole system without giving much thought to the CPU. "The GPU is the star of a machine learning system, so surely the CPU doesn't need much attention?" Actually, that is
LLM
Hello! MCP is spreading through the LLM industry at breakneck speed, and today we want to focus specifically on the implementation side. We say "MCP" as if it were a single thing, but the specification people call the "standard" has actually changed quite a bit in
Blog
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
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.
LLM
Introduction This report analyzes the performance of Japanese-capable LLMs based on Nejumi Leaderboard 4 benchmark data (October 11, 2025 edition), offering a comprehensive picture of the field. Nejumi Leaderboard 4 is known as a highly reliable benchmark that evaluates LLM performance on Japanese-language tasks from multiple angles. In this analysis,
LLM
Hello! In this article, we take a detailed look at how image token counts are calculated when using Claude 4.5 Sonnet/Haiku and Claude 4.1 Opus via the API. How Image Token Counts Are Calculated Images sent to the Claude 4.5 API are counted as tokens, just
Python
Hello! When writing custom classes in Python, have you ever run into the baffling situation where "the object clearly exists, but an if statement judges it False" ? In this article, we explain the unexpected truthiness behavior that arises when you implement the __len__ method! A Bug We Actually
Daily Dev Tips
Hello! In this post, we look at how to resolve the "libcudnn.so.9: cannot open shared object file" error that can occur during GPU inference with ONNX Runtime. When running GPU inference with ONNX Runtime, you may run into a CUDA provider initialization error. This article explains
PyTorch
Hello! In this post, we explain how to deal with the following problem in a PyTorch 2.6.0 environment. NVIDIA GeForce RTX 5090 with CUDA capability sm_120 is not compatible with the current PyTorch installation. The current PyTorch install supports CUDA capabilities sm_50 sm_60 sm_70