森茂洋 / Hiroshi Morishige | DevelopersIO

produced by Classmethod

製造ビジネステクノロジー部テクニカルリードエンジニア. フロントエンドが主戦場です

森茂洋 / Hiroshi Morishigemorishige-hiroshi

Posts per Month

118Posts

Organizing How to Use and Find the Agent Skills Distributed by NVIDIA

森茂洋 / Hiroshi Morishige

2026.11.03

I tried running the 4GB conversational model "Nemotron 3.5 Bolt E4B" on DGX Spark

森茂洋 / Hiroshi Morishige

2026.10.24

I summarized Jensen Huang's keynote at GTC Berlin 2026

森茂洋 / Hiroshi Morishige

2026.10.21

Tried Running the Image-Capable 120B MoE "Nemotron 3.5 Super VL 120B-A12B" on DGX Spark

森茂洋 / Hiroshi Morishige

2026.10.18

I ran the 2-bit quantized MoE "Nemotron 3.5 Bolt 74B-A9B" on DGX Spark

森茂洋 / Hiroshi Morishige

2026.10.16

I tried the non-generative diffusion model Nemotron Deciffusion 8B on DGX Spark

森茂洋 / Hiroshi Morishige

2026.10.15

I read about what changed in Qwik 2.0 RC and the design philosophy behind trimming even HTML comments

森茂洋 / Hiroshi Morishige

2026.10.03

I Tried a Non-Generative Decision Model, CLM, as the Judge for Switchyard on DGX Spark

森茂洋 / Hiroshi Morishige

2026.09.27

Tried running Pi sub-agents per sandbox with NVIDIA OpenShell 0.1.0 series

森茂洋 / Hiroshi Morishige

2026.09.26

I tried using Nemotron 3.5 Lightning as the judge, making it a single-token judgment that doesn't generate like Jev

森茂洋 / Hiroshi Morishige

2026.09.23

I read OpenJev and thought of an alternative solution using non-generative AI

森茂洋 / Hiroshi Morishige

2026.09.18

I tried running NeMo AutoModel, which can train Hugging Face models as-is, on DGX Spark

森茂洋 / Hiroshi Morishige

2026.09.15

I thought about AI agent Memory from the perspectives of correction, inspection, and deletion

森茂洋 / Hiroshi Morishige

2026.09.07

ちょっと話題の記事

I compared Qwen3 8B and GLM Z1 9B Flash across 4 configurations by use case on DGX Spark

森茂洋 / Hiroshi Morishige

2026.09.06

I thought about a configuration for delivering reasoning models to the field on NVIDIA Jetson

森茂洋 / Hiroshi Morishige

2026.09.05

ちょっと話題の記事

I tried running GLM-5.3-Flash 320B on 2 DGX Spark units and measured whether using 2 units is worth it

森茂洋 / Hiroshi Morishige

2026.09.01

I tried repurposing Nemotron Lightning as a dedicated judge for a team assistant using SFT and Capability Cards

森茂洋 / Hiroshi Morishige

2026.09.01

話題の記事

I tested the practical boundary by running 320B GLM-5.3-Flash on a single DGX Spark

森茂洋 / Hiroshi Morishige

2026.08.30

Thinking About the Ideal AI Gateway and Router for Using Coding Agents in a Team

森茂洋 / Hiroshi Morishige

2026.08.30

I thought about how to use NVIDIA NeMo Relay and NeMo Switchyard as an AI Gateway

森茂洋 / Hiroshi Morishige

2026.08.29

I looked into how the prefill router in NVIDIA NeMo Switchyard works

森茂洋 / Hiroshi Morishige

2026.08.22

I tried NVIDIA's new agent framework NOOA with a local LLM on DGX Spark

森茂洋 / Hiroshi Morishige

2026.08.18

I tried setting up a development environment by connecting the Pi coding agent to Switchyard

森茂洋 / Hiroshi Morishige

2026.08.17

I tried fine-tuning Nemotron 3.5 Lightning with LoRA post-training to make it a judge for an LLM router

森茂洋 / Hiroshi Morishige

2026.08.16

I tried NVIDIA Nemotron 3.5 Lightning 30B-A3B-NVFP4

森茂洋 / Hiroshi Morishige

2026.08.12

I tried NeMo Switchyard v0.2.0 reborn in Rust

森茂洋 / Hiroshi Morishige

2026.08.12

I tried attaching eyes and ears to DeepSeek V4 Flash, which doesn't support vision, using Qwen-MM-Plugins

森茂洋 / Hiroshi Morishige

2026.08.11

I tried running Meta's open-weight Muse Glimmer 30B on DGX Spark

森茂洋 / Hiroshi Morishige

2026.08.11

ちょっと話題の記事

Tried running DeepSeek V4 Flash-0731 at 284B on two DGX Spark units

森茂洋 / Hiroshi Morishige

2026.08.10

Open-weight model team AI environment that covers everything from development to business use

森茂洋 / Hiroshi Morishige

2026.08.08

I tried building a team-shared RAG using NVIDIA RAG Blueprint × DGX Spark and connecting it with MCP

森茂洋 / Hiroshi Morishige

2026.08.07

話題の記事

Tried running Kimi K3 2.8T on a single DGX Spark

森茂洋 / Hiroshi Morishige

2026.08.06

I attended NVIDIA Japan's NPN Partner Model Customization Bootcamp

森茂洋 / Hiroshi Morishige

2026.08.06

I tried NVIDIA's agent execution runtime NeMo Relay

森茂洋 / Hiroshi Morishige

2026.08.06

話題の記事

Tried running DeepSeek V4 Flash-0731 on a single DGX Spark with llama.cpp

森茂洋 / Hiroshi Morishige

2026.08.02

必見の記事

I tried to organize the state of local LLMs in the summer of 2026

森茂洋 / Hiroshi Morishige

2026.07.24

Tried running the 118B code-specialized MoE "Laguna S 2.1" on DGX Spark

森茂洋 / Hiroshi Morishige

2026.07.23

ちょっと話題の記事

I also compared two quantized versions of Gemma 4 NVFP4 on DGX Spark

森茂洋 / Hiroshi Morishige

2026.07.18

I attended Build a Claw Tokyo, where Jensen Huang, the CEO, also made a surprise appearance.

森茂洋 / Hiroshi Morishige

2026.07.16

A new champion among partner LLMs for DGX Spark? Comparing Qwen3.6-35B-A3B-NVFP4 in two quantized versions

森茂洋 / Hiroshi Morishige

2026.07.13

ちょっと話題の記事

I thought about an LLM configuration that partners with one DGX Spark

森茂洋 / Hiroshi Morishige

2026.07.06

I tried running NVIDIA's time series foundation model NV-Tesseract on DGX Spark after it was released as open source

森茂洋 / Hiroshi Morishige

2026.07.04

I tried NVIDIA's new LLM routing infrastructure NeMo Switchyard

森茂洋 / Hiroshi Morishige

2026.07.03

ちょっと話題の記事

Tried running DeepSeek V4 Flash-DSpark on 2 DGX Spark units

森茂洋 / Hiroshi Morishige

2026.06.30

I tried Hermes Agent's Mixture of Agents (MoA)

森茂洋 / Hiroshi Morishige

2026.06.29

ちょっと話題の記事

I ran Ornith 1.0 on DGX Spark and compared its Japanese language performance with Gemma 4 / Nemotron

森茂洋 / Hiroshi Morishige

2026.06.28

I tried out OpenRouter's MCP Server

森茂洋 / Hiroshi Morishige

2026.06.27

I participated in NVIDIA Japan's NPN Partner Agentic AI Bootcamp.

森茂洋 / Hiroshi Morishige

2026.06.24

ちょっと話題の記事

I tried PLaMo 3.0 Prime

森茂洋 / Hiroshi Morishige

2026.06.22

必見の記事

I tried Sakana Fugu (GA) with a subscription plan

森茂洋 / Hiroshi Morishige

2026.06.22

I tried running NVIDIA VSS 3.2.0 GA on DGX Spark

森茂洋 / Hiroshi Morishige

2026.06.22

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

森茂洋 / Hiroshi Morishige

2026.06.21

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

森茂洋 / Hiroshi Morishige

2026.06.21

I tried running Codex confined in NVIDIA OpenShell

森茂洋 / Hiroshi Morishige

2026.06.20

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

森茂洋 / Hiroshi Morishige

2026.06.18

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

森茂洋 / Hiroshi Morishige

2026.06.18

I tried to have NemoHermes read a private repository without passing a GitHub token

森茂洋 / Hiroshi Morishige

2026.06.17

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

森茂洋 / Hiroshi Morishige

2026.06.08

I tried reading Hermes Agent's self-improving from the code

森茂洋 / Hiroshi Morishige

2026.06.06

注目の記事

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

森茂洋 / Hiroshi Morishige

2026.06.05