close

DEV Community

soy profile picture

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.

[01] Building a Personal ALM System — Your Life as a Database Schema

[01] Building a Personal ALM System — Your Life as a Database Schema

Comments
6 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.

Already have an account? Sign in
Claude Code Unleashes AI Workflow Routines & Autoresesearch Agents for Production

Claude Code Unleashes AI Workflow Routines & Autoresesearch Agents for Production

Comments
3 min read
DuckDB 1.5.2, SQLite JSON Join Speedup, & Postgres NOTIFY Debugger

DuckDB 1.5.2, SQLite JSON Join Speedup, & Postgres NOTIFY Debugger

Comments
3 min read
LLM Auto-Tunes llama.cpp, SASS Latency Analysis, DLSS Frame Gen for RTX 40

LLM Auto-Tunes llama.cpp, SASS Latency Analysis, DLSS Frame Gen for RTX 40

Comments
3 min read
Anthropic Preps Opus 4.7, Claude Code Gains Routines & Autoresearch Plugin

Anthropic Preps Opus 4.7, Claude Code Gains Routines & Autoresearch Plugin

Comments
3 min read
Boosting llama.cpp with Auto-Tuning, Qwen Quantization Benchmarks, & Mobile Ollama AI Servers

Boosting llama.cpp with Auto-Tuning, Qwen Quantization Benchmarks, & Mobile Ollama AI Servers

Comments
3 min read
Coinbase AI Agent Prompt Injection, Dolibarr RCE, & WordPress Supply Chain Backdoors

Coinbase AI Agent Prompt Injection, Dolibarr RCE, & WordPress Supply Chain Backdoors

Comments
3 min read
LLM Prompting, AI-Generated Code Discussions & Python Workflow Automation

LLM Prompting, AI-Generated Code Discussions & Python Workflow Automation

Comments
3 min read
DuckDB Lake, dbt Custom Materializations, & PostgreSQL Partitioning Strategies

DuckDB Lake, dbt Custom Materializations, & PostgreSQL Partitioning Strategies

Comments
3 min read
CUDA-Accelerated EEG, AMD RX 9070 XT Power Melts, & Strix Halo LPDDR5X Specs

CUDA-Accelerated EEG, AMD RX 9070 XT Power Melts, & Strix Halo LPDDR5X Specs

Comments
3 min read
Claude API Cache TTL & Model Switching, TurboOCR for High-Speed AI

Claude API Cache TTL & Model Switching, TurboOCR for High-Speed AI

Image Image 2
Comments
3 min read
Llama4 108B Local Inference, MiniMax M2.7 GGUF Alert, & Ollama Security Scanner

Llama4 108B Local Inference, MiniMax M2.7 GGUF Alert, & Ollama Security Scanner

Image Image 2
Comments
3 min read
Actively Exploited Adobe CVE, Supply Chain Malware, & Self-hosted Certs

Actively Exploited Adobe CVE, Supply Chain Malware, & Self-hosted Certs

Comments
3 min read
LLM Agent Workflows: Local AI Support, Prompt Tooling, & Claude Code API Costs

LLM Agent Workflows: Local AI Support, Prompt Tooling, & Claude Code API Costs

Comments
4 min read
PostgreSQL Credential Rotation, pgvector HALFVEC, & SQLite Type Affinity

PostgreSQL Credential Rotation, pgvector HALFVEC, & SQLite Type Affinity

Comments
3 min read
Claude Code API Token & Reliability Issues, New Multi-Agent Framework

Claude Code API Token & Reliability Issues, New Multi-Agent Framework

Comments
3 min read
llama.cpp Adds Gemma 4 Audio, Speculative Decoding & Ollama Agent Boost Local AI

llama.cpp Adds Gemma 4 Audio, Speculative Decoding & Ollama Agent Boost Local AI

Comments
3 min read
AI & Supply Chain Security: Prompt Injection Suite, Nginx CVE, & Rockstar Breach

AI & Supply Chain Security: Prompt Injection Suite, Nginx CVE, & Rockstar Breach

Comments
3 min read
Applied AI with Python: Firecrawl RAG, Decentralized Models & Streamlit Workflows

Applied AI with Python: Firecrawl RAG, Decentralized Models & Streamlit Workflows

Comments
3 min read
PostgreSQL EXPLAIN ANALYZE Viewer, Checkpoints & SQLite JSON Parsing

PostgreSQL EXPLAIN ANALYZE Viewer, Checkpoints & SQLite JSON Parsing

Comments
3 min read
RTX 5090 cuBLAS Bug, Neural Texture Compression, Multi-GPU vLLM Inference

RTX 5090 cuBLAS Bug, Neural Texture Compression, Multi-GPU vLLM Inference

Comments
3 min read
Claude API Fallback, Code Performance Drop, & n8n Integrations

Claude API Fallback, Code Performance Drop, & n8n Integrations

Comments
3 min read
Local Inference Accelerated: DFlash MLX, vLLM Qwen, Ollama Consumer Guides

Local Inference Accelerated: DFlash MLX, vLLM Qwen, Ollama Consumer Guides

Comments
3 min read
Critical CVEs, AI RCE, & Supply Chain Malware Hits HWMonitor

Critical CVEs, AI RCE, & Supply Chain Malware Hits HWMonitor

Comments
4 min read
Smriti: Hybrid Vector DB for AI Agents, Claude Code LSP Integration & Workflow Automation with LLMs

Smriti: Hybrid Vector DB for AI Agents, Claude Code LSP Integration & Workflow Automation with LLMs

Comments
3 min read
PostgreSQL O(delta) MV Refreshes, pg_lake for Data Lakes, & ADBC for Columnar Data

PostgreSQL O(delta) MV Refreshes, pg_lake for Data Lakes, & ADBC for Columnar Data

Comments
3 min read
CUDA SGEMM Bug on RTX 5090, Kernel-Fusing for SGEMV, & Radeon RX 9070 XT Price Surge

CUDA SGEMM Bug on RTX 5090, Kernel-Fusing for SGEMV, & Radeon RX 9070 XT Price Surge

Comments
4 min read
Claude AI Expands Enterprise Features, Developer Tools & CLI Automation

Claude AI Expands Enterprise Features, Developer Tools & CLI Automation

Comments
3 min read
Gemma4 Tool Calling Fixes in llama.cpp, RTX cuBLAS MatMul Bug, & Local Ollama + Whisper UI

Gemma4 Tool Calling Fixes in llama.cpp, RTX cuBLAS MatMul Bug, & Local Ollama + Whisper UI

Comments
3 min read
CUPS RCE-to-Root, AI Sandbox Escape, & LittleSnitch for Linux

CUPS RCE-to-Root, AI Sandbox Escape, & LittleSnitch for Linux

Comments
3 min read
AI Agents: Cost-Optimized Orchestration & Robust Text-to-SQL with Python

AI Agents: Cost-Optimized Orchestration & Robust Text-to-SQL with Python

Comments
4 min read
SQLite Join Benchmarks, PostgreSQL for AI Graphs with pgvector, & pGenie for SQL Validation

SQLite Join Benchmarks, PostgreSQL for AI Graphs with pgvector, & pGenie for SQL Validation

Comments
3 min read
LLM GPU Breakthroughs: RT Cores, Llama.cpp Parallelism, AMD Optimizations

LLM GPU Breakthroughs: RT Cores, Llama.cpp Parallelism, AMD Optimizations

Comments
3 min read
Cloud AI & Dev: Gemini 3D, Claude Agent Patterns, Embedding Compression

Cloud AI & Dev: Gemini 3D, Claude Agent Patterns, Embedding Compression

Comments
4 min read
Llama.cpp Tensor Parallelism, Gemma 4 Stability, & OmniVoice Local TTS

Llama.cpp Tensor Parallelism, Gemma 4 Stability, & OmniVoice Local TTS

Comments
3 min read
LLM Code Vulnerabilities, GRU Router Exploits & `dnsight` CLI DNS Auditor

LLM Code Vulnerabilities, GRU Router Exploits & `dnsight` CLI DNS Auditor

Comments
3 min read
Anthropic Launches Managed Agents, Optimize LLM Context, Python Memory Needed

Anthropic Launches Managed Agents, Optimize LLM Context, Python Memory Needed

Comments
3 min read
SQLite Internals, PostgreSQL Extensions & Performance Tuning Updates

SQLite Internals, PostgreSQL Extensions & Performance Tuning Updates

Comments
3 min read
New AMD RX 9000 GPUs, DLSS/FSR Mod, & Deep Dive into CUDA LLVM Bitcode

New AMD RX 9000 GPUs, DLSS/FSR Mod, & Deep Dive into CUDA LLVM Bitcode

Comments
3 min read
Anthropic Launches Managed Agents; Claude Opus 4.6 Reasoning Fluctuation, and Code Resurrections

Anthropic Launches Managed Agents; Claude Opus 4.6 Reasoning Fluctuation, and Code Resurrections

Comments
4 min read
Gemma 4 GGUFs, CLI Coding Agent, & Pi 5 Ollama Benchmarks Lead Local AI

Gemma 4 GGUFs, CLI Coding Agent, & Pi 5 Ollama Benchmarks Lead Local AI

Comments
3 min read
Nissan PSR Simulation

Nissan PSR Simulation

Comments
9 min read
Why I’m Engineering My FIRE with Python — A Manifesto

Why I’m Engineering My FIRE with Python — A Manifesto

Image 1
Comments
5 min read
Why I’m Engineering My FIRE with Python — A Manifesto

Why I’m Engineering My FIRE with Python — A Manifesto

Comments
6 min read
Cloud Supply Chain & AWS CodeBuild PrivEsc Exposed; GDDR6 Rowhammer to Root Shell

Cloud Supply Chain & AWS CodeBuild PrivEsc Exposed; GDDR6 Rowhammer to Root Shell

Comments
3 min read
Claude Code Powers AI Workflows: Ultraplan for Agent Orchestration & App Store Automation

Claude Code Powers AI Workflows: Ultraplan for Agent Orchestration & App Store Automation

Comments
3 min read
SQLite Internals: Memory Leak, Security Vuln; PostgREST Goes Edge

SQLite Internals: Memory Leak, Security Vuln; PostgREST Goes Edge

Comments
3 min read
CUDA Memory Hierarchy, Tile Programming, & DLSS 310.6 Driver Enhancements

CUDA Memory Hierarchy, Tile Programming, & DLSS 310.6 Driver Enhancements

Comments
3 min read
Claude Code Enhances Dev Workflows, Open-Source AI Outperforms Sonnet on Benchmarks

Claude Code Enhances Dev Workflows, Open-Source AI Outperforms Sonnet on Benchmarks

Comments
3 min read
Gemma 4 Benchmarks, iMac G3 Local LLM, and Ollama Android Client for On-Device Inference

Gemma 4 Benchmarks, iMac G3 Local LLM, and Ollama Android Client for On-Device Inference

Comments
3 min read
Zero-Days, Supply Chain & AI Self-Jailbreaks: Top Security Threats

Zero-Days, Supply Chain & AI Self-Jailbreaks: Top Security Threats

Image 1
Comments
3 min read
AI Agent Autonomy, Audio Transcription Models, & LLM Token Optimization

AI Agent Autonomy, Audio Transcription Models, & LLM Token Optimization

Comments
3 min read
PostgreSQL Performance in the Spotlight: Linux 7.0 Impact, Benchmarking & Vacuum Tuning

PostgreSQL Performance in the Spotlight: Linux 7.0 Impact, Benchmarking & Vacuum Tuning

Comments
3 min read
Hopper/Blackwell Tensor Core Optimization, llama.cpp VRAM Fix & 4W NPU Inference

Hopper/Blackwell Tensor Core Optimization, llama.cpp VRAM Fix & 4W NPU Inference

Comments
3 min read
Claude Ultraplan & API Access Changes for Developers; Cadenza Boosts AI Agent Research

Claude Ultraplan & API Access Changes for Developers; Cadenza Boosts AI Agent Research

Comments
4 min read
Gemma 4 Local Inference: Ollama Benchmarks, llama.cpp KV Cache Fix, NPU Deployments

Gemma 4 Local Inference: Ollama Benchmarks, llama.cpp KV Cache Fix, NPU Deployments

Comments
2 min read
Self-Hosting Docker Mastery, Rust/WASM Browser Engines, & Gesture-Controlled Web

Self-Hosting Docker Mastery, Rust/WASM Browser Engines, & Gesture-Controlled Web

Comments
4 min read
PostgreSQL Performance Crisis, Cloud-Native DB Deployments, & Collation Deep Dive

PostgreSQL Performance Crisis, Cloud-Native DB Deployments, & Collation Deep Dive

Comments
4 min read
Agent Frameworks & Local VLM Tuning: Boosting Dev Productivity

Agent Frameworks & Local VLM Tuning: Boosting Dev Productivity

Comments
4 min read
GPU Power Tools & CUDA Deep Dives for Local LLM Builders

GPU Power Tools & CUDA Deep Dives for Local LLM Builders

Comments
3 min read
loading...