soy

Patent lawyer turned AI engineer. Processed 4M patents with local LLM on RTX 5090. Building PatentLLM — AI-powered patent search. Also ranked #1 on Floodgate (shogi AI). Writing about local LLM etc.

Japan Joined on Mar 8, 2026 q07025a@gmail.com https://media.patentllm.org/

soy

Mar 28

Self-Host Like a Pro: From Security Tools to 100x Faster AI Agent Sandboxing

#webdev #devops #cloud

3 min read

Want to connect with soy?

Create an account to connect with soy. You can also sign in below to proceed if you already have an account.

Create Account

Already have an account? Sign in

soy

Mar 28

SQLite, Go/Postgres, & Petabytes: Database Patterns for Builders

#database #sql #dataengineering

4 min read

soy

Mar 28

Local LLMs & Agents: Build Real-time Deepfakes, Agent Frameworks & AI Scientists

#devtools #programming #ai

3 min read

soy

Mar 28

Boost Local LLMs: TurboQuant KV Cache, Fast Cold Starts, & Rust GPU Dev

#gpu #ai #performance

4 min read

soy

Mar 28

Local LLM Efficiency & Security: TurboQuant Innovations and Supply Chain Alerts

#ai #machinelearning #llm

3 min read

soy

Mar 27

Self-Host Strong, AI Agents Fast, & Master Your JSON Tools

#webdev #devops #cloud

3 min read

soy

Mar 27

Building High-Performance Data Stacks: Vector Search, SQLite Ops, & Open-Source Monitoring

#database #sql #dataengineering

4 min read

soy

Mar 27

Local AI Agents, Voice Models & Self-Hosted Research Tools

#devtools #programming #ai

4 min read

soy

Mar 27

Local LLM Power-Ups: Voxtral TTS, TurboQuant, & Sub-Second Cold Starts

#gpu #ai #performance

3 min read

soy

Mar 27

GPU-Accelerated LLMs: Serving at 1M Tok/s, Voxtral TTS, & 4-bit Weight Quantization

#ai #machinelearning #llm

3 min read

soy

Mar 26

DIY Compute: Tesla Hacking, RAG Systems, and Blazing Fast AI Agents

#webdev #devops #cloud

4 min read

soy

Mar 26

Building & Monitoring Data Backends: Tools, Architecture, and Observability

#database #sql #dataengineering

4 min read

soy

Mar 26

Cutting-Edge AI Agents: Building Multi-Agent Workflows Locally

#devtools #programming #ai

3 min read

soy

Mar 26

Local LLM Unleashed: Faster Inference, Instant Starts, & Open TTS

#gpu #ai #performance

4 min read

soy

Mar 26

Local LLM Acceleration: Quantization, TTS, and 1M Tokens/Sec

#ai #machinelearning #llm

4 min read

soy

Mar 26

vLLM On-Demand Gateway: Zero-VRAM Standby for Local LLMs on Consumer GPUs

#vllm #llm #gpu #python

4 min read

soy

Mar 26

Databases Are the New AI Moat: Why DB-First Architecture Changes Everything

#database #ai #architecture #sqlite

5 min read

soy

Mar 25

Local LLM Apps, Persistent Certs & K8s Storage Mastery

#webdev #devops #cloud

4 min read

soy

Mar 25

DIY Data Stacks: Building, Optimizing, and Self-Hosting Your Data Infrastructure

#database #sql #dataengineering

3 min read

soy

Mar 25

Next-Gen LLM Dev: APIs, Agents, and Accessible Local Inference

#devtools #programming #ai

4 min read

soy

Mar 25

New Arc GPUs, Supply Chain Security, and Deep CUDA Optimization

#gpu #ai #performance

3 min read

soy

Mar 25

Local LLMs & Edge AI: Hardware Boost, Security Fixes, and Extreme Compression

#ai #machinelearning #llm

4 min read

soy

Mar 24

Urgent Security Alerts & Self-Hosted Swarm: Building Local LLM Infra Safely

#webdev #devops #cloud

3 min read

soy

Mar 24

New Local-First SQL Tools, Vector Database MVCC, & AI Agent Query Risks

#database #sql #dataengineering

3 min read

soy

Mar 24

Local AI Agents, Scalable Memory, and Multimodal Creation: Top Dev Tools

#devtools #programming #ai

3 min read

soy

Mar 24

Local LLM Security Criticals, Rust on GPU, & Deep Dive into PTX Optimization

#gpu #ai #performance

3 min read

soy

Mar 24

Local LLM Revolution: Speed, Security, and Million-Token Contexts

#llm #ai #opensource

3 min read

soy

Mar 24

AI's Infrastructure & Agents: From Chips to Code Automation

#ai #machinelearning #llm

4 min read

soy

Mar 24

I Built a SQLite Editor in 180 Lines, Then Rebuilt It in 380 for the Browser

#devtools #python #productivity

3 min read

soy

Mar 23

Vision and Hardware Strategy Shaping the Future of AI: From Apple to AGI and AI Chips

#ai #machinelearning #llm

3 min read

soy

Mar 23

The Future of Open Source and Security: From Geopolitics to Threats in the Development Field

#webdev #devops #infrastructure

4 min read

soy

Mar 23

The Forefront of Development Efficiency with AI Agents: From OSS to Code Review

#devtools #python #productivity

3 min read

soy

Mar 23

The Dawn of the Local AI Era: From iPhone 17 Pro to the Future of NVIDIA RTX

#ai #gpu #performance

3 min read

soy

Mar 23

Today's LLM Frontier: From the Breakthrough of Kimi K2.5 to GPT-5.4/Gemini Flash-Lite

#ai #llm #machinelearning

3 min read

soy

Mar 23

Canonical Eyes IPO — Ubuntu Proves the Revival of Linux and OSS

#programming

3 min read

soy

Mar 22

Developer Security and AI Industry Trends: Langflow Vulnerability, Cargo Advisory, and the State of AI at GDC

#devtools #python #productivity

3 min read

soy

Mar 22

AI and Cloud Infrastructure Convergence: Innovations in Cloudflare Workers AI, Project Nomad, and Trainium

#webdev #devops #infrastructure

3 min read

soy

Mar 22

Next-Generation LLM Inference Technology: From Flash-MoE to Gemini Flash-Lite, and Local GPU Utilization

#ai #gpu #performance

3 min read

soy

Mar 22

The Wave of Open-Source AI and Investment in Security: Trends from Qwen, MS, and Google

#ai #llm #machinelearning

3 min read

soy

Mar 22

Current Frontline in AI Agent Development: Robust Agent Design and Security Measures

#ai #machinelearning #llm

3 min read

soy

Mar 22

Running Karpathy's autoresearch with Local LLM — Zero API Cost Autonomous AI Research

#ai #machinelearning #llm

3 min read

soy

Mar 22

Built a Local-First RAG Research Tool with Nemotron + vLLM + Tool Calling

#ai #machinelearning #llm

2 min read

soy

Mar 22

AI Era Security and OSS: Trivy Compromise, Google and Cloudflare's Countermeasures

#ai #machinelearning #llm

3 min read

soy

Mar 22

Frontiers of AI Agent Development: Claude HUD, OpenAI Monitoring, and the Impact of Astral Acquisition

#devtools #python #productivity

3 min read

soy

Mar 22

Today's Local LLM Acceleration Techniques: ik_llama.cpp Speedup, Tinybox, and NVIDIA GTC Latest Trends

#ai #gpu #performance

3 min read

soy

Mar 22

AI Questions the Future of the Internet: Freedom, Quality Decline, and Content Reliability

#webdev #devops #infrastructure

7 min read

soy

Mar 22

Data Preparation and Security to Accelerate AI Development: Leveraging Open Source Tools

#devtools #python #productivity

6 min read

soy

Mar 22

Next-Gen LLMs: Deep Dive into Compact, High-Speed Models and Temporal Reasoning – Gemini 3.1 Flash-Lite, GPT-5.4 mini/nano

#ai #llm #machinelearning

7 min read

soy

Mar 21

AI Agent Safety and Operations: Frontline Measures Against Prompt Injection and Monitoring

#ai #machinelearning #llm

6 min read

soy

Mar 21

2026: Local AI Evolves! From Offline Devices to Large-Scale Inference on RTX

#ai #gpu #performance

5 min read

soy

Mar 21

New Synergy of Cloud and AI: Cloudflare Workers AI, Google's OSS Security, and AI Integration in WordPress

#webdev #devops #infrastructure

5 min read

soy

Mar 21

RTX 40 Series Makes LLM Blazing Fast! The Complete Guide to Inference Optimization for Individual Developers [2026 Latest Edi...

#ai #gpu #performance

7 min read

soy

Mar 21

The Real Inflection Point GTC 2026 Quietly Announced — Why NVIDIA Bet on "Open"

#ai #machinelearning #llm

9 min read

soy

Mar 21

Training a Shogi Engine: ONNX Conversion, TensorRT, and Getting Crushed by Ryfamate

#ai #machinelearning #python #gamedev

4 min read

soy

Mar 21

Lennart Poettering and the systemd Wars: The Most Controversial Software in Linux History

#linux #devops #sysadmin #opensource

6 min read

soy

Mar 21

The README Trap: Why AI Coding Assistants Skip Your Docs (and 3 Fixes)

#ai #documentation #productivity #devops

4 min read

soy

Mar 21

From 30 Seconds to 3 Milliseconds: Replacing LIKE with FTS5 on 1.7M Patent Records

#sqlite #database #performance #search

4 min read

soy

Mar 21

SoyLM: Building a Zero-Dependency Local RAG Tool in a Single Python File

#python #ai #rag #opensource

5 min read

soy

Mar 21

Adding Stripe Checkout to a Solo SaaS: Lessons from PatentLLM's $1K/mo Plan

#stripe #saas #python #startup

4 min read

soy

Mar 21

When Gemini Hallucinates Patent Numbers: Fixing the FTS5 + LLM Analysis Pipeline

#ai #sqlite #search #llm

3 min read

1 Week Community Wellness Streak

Writing Debut

Want to connect with soy?