Tag

#ローカルLLM

Articles tagged with "ローカルLLM", sorted from newest to oldest.

6 articles
Read article
An illustration showing dots connected by thin lines branching into two paths, with a blue check mark on one and an X mark on the other
AI By Terisuke

Adding Examples Can Make Some Prompts Worse: Testing Generative AI with a Small LLM

On October 29, 2026, at an internal corporate study session led by Representative Kousuke Terada, we tested two techniques on a small language model (Qwen2.5-3B-Instruct): "providing examples" and "asking for a review." Based on questions that improved, worsened, or confidently asserted an error was correct, we explain how to evaluate generative AI for business operations.

#生成AI #ローカルLLM #プロンプト +2
Read article
An explanatory illustration showing servers and terminals separated by transparent enclosures
AI By Terisuke

From Patch Release to Application: Considering Update Responsibilities, Deadlines, and Records Through LiteLLM

Using LiteLLM's patch distribution via private registries as a starting point, this article explores update responsibilities, application deadlines, and record-keeping for local LLMs. A guide for companies to separately verify the release of a patch and its application to their internal environment.

#LiteLLM #ローカルLLM #セキュリティ +1
Read article
AI By Terisuke

Before using a local inference API inside the company: designing authentication, an allow list and device retirement

Before using a local inference API inside the company, design authentication, an allow list and device retirement as separate things. An allow list shows which peer may be reached. Who may use it for which work is decided separately.

#ローカルLLM #Ollama #情報セキュリティ +1
Read article
AI By Terisuke

Where to separate field AI and internal-document AI. Cor.Inc.'s design choice

Field AI that runs near cameras and sensors, and a local LLM that handles internal documents, care about different conditions. Cor.Inc.'s policy is to separate the verification environments. Separation itself is not proof of safety.

#ローカルLLM #エッジAI #セキュアAI +1
Read article
AI By Terisuke

What Information Can and Cannot Be Entered into ChatGPT at Work: Criteria for Using AI with Confidential Data

For executives and administrative departments unsure whether they can input contracts, meeting minutes, estimates, or customer information into generative AI, this article explains how to classify confidentiality levels, choose between cloud AI and local LLMs, and establish internal rules.

#生成AI #情報セキュリティ #ChatGPT +1
Read article
AI By Terisuke

What Is a Local LLM? A Realistic Guide to AI Adoption Without Exposing Confidential Data

We explain the basics of local LLMs, how they differ from cloud AI, the types of operations best suited for adoption, and the security and operational requirements to verify before a PoC. This article is for companies looking to securely leverage AI with confidential data.

#ローカルLLM #セキュアAI #機密データ