produced by Classmethod

# LLM articles

Large Language Modelの略称で、GPT-3やChatGPTなどの大規模な言語モデルを指します。

I tried Sakana Fugu (GA) with a subscription plan

2026.06.22

I tried running NVIDIA VSS 3.2.0 GA on DGX Spark

2026.06.22

[Update] I Tried Agentic Search That Converts Natural Language to Search DSL Using Amazon OpenSearch Serverless NextGen × Amazon Bedrock (Claude)

2026.06.21

I tried retraining the NVIDIA LLM Router to match my own persona (Training Edition)

2026.06.21

I tried building an environment for using LLMs differently by purpose with NVIDIA LLM Router (Basics Edition)

2026.06.21

I tried running Codex confined in NVIDIA OpenShell

2026.06.20

I thought about the retail store version of NVIDIA FOX Blueprint with VSS Skills and Hermes Agent

2026.06.18

I thought about a Mini-FOX configuration to start small with the NVIDIA FOX Blueprint

2026.06.18

I tried having NemoHermes read a private repository without passing a GitHub token

2026.06.17

DevRev: What AI Knowledge Management May Need Is a Garbage Collector

越井琢巳 (Koshii Takumi)

2026.06.13

Tracing the Lineage of AI Code with Agent Trace × Jujutsu

2026.06.11

ちょっと話題の記事

I tried out Claude Fable 5, which has become available on Amazon Bedrock

2026.06.10

Claude Code v2.1.170 Major Update - Now featuring Mythos Class 1 Model Claude Fable 5!

2026.06.10

I tried to analyze the updated NVIDIA Physical AI in Cosmos 3 through the three-tier structure of factory AI

2026.06.08

I tried reading the self-improving of Hermes Agent from the code

2026.06.06

I tried out the interactive shell feature of Amazon Bedrock AgentCore Runtime

2026.06.06

注目の記事

Since a 12B was added to Gemma 4, I tried testing Japanese performance, voice input, and MTP on the DGX Spark

2026.06.05

ちょっと話題の記事

I tried NVIDIA Nemotron 3 Ultra

2026.06.05

I organized a usage map for the NVIDIA Cosmos 3 family

2026.06.02

I tried running NVIDIA Cosmos 3 on DGX Spark

2026.06.01

Trying out the Claude Files API

2026.05.30

Detecting documentation gaps before AI model release? A breakdown of how the NVIDIA MCG Toolkit works

2026.05.30

[Update] Claude Opus 4.8 is now available on Amazon Bedrock

2026.05.29

A GitHub Action has been added to automatically evaluate LLM accuracy in CI with Langfuse

2026.05.26

I tried predicting PLC-style time series data with Chronos-2 and generating maintenance comments with Nemotron

2026.05.26

Let me try detecting the causes of Claude's prompt cache failures

2026.05.26

I ran Nemotron-Labs-Diffusion on DGX Spark and actually measured tri-mode generation

2026.05.21

I thought about practical use cases for NVIDIA VSS + AI Agents + Skills in familiar real-world settings

2026.05.16

I investigated the current state of manufacturing VSS as seen at NVIDIA VSS 3.1.0 EA and Hannover Messe

2026.05.10

I tried Vercel AI Gateway as an OpenRouter user

越井琢巳 (Koshii Takumi)

2026.05.01

I tried out the AI troubleshooting feature in AWS Deadline Cloud

越井琢巳 (Koshii Takumi)

2026.04.27

必見の記事

Testing Gemma 4 Local Execution on MacBook (16GB) — From Model Selection with Ollama to UI Building and Practical Project Implementation

2026.04.09

注目の記事

Tried to run Gemma 4 locally at its limit (31b q8) on M1 Max 64GB

小渕ヒューゴ

2026.04.06

When I tried three subjects with Godot and Codex, I could see the strength of the initial output and the burden of manual verification

越井琢巳 (Koshii Takumi)

2026.03.18

ちょっと話題の記事

I tried running NVIDIA Nemotron 3 Super on DGX Spark

2026.03.12

注目の記事

Building a Private LLM Environment (Qwen 3.5-4B) on AWS That Can Be Used from Both Smartphones and PCs

越井琢巳 (Koshii Takumi)

2026.03.05