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.

Zero-Day Exploits, GitHub Actions Supply Chain Attacks, and OTP Auth Flaws

Zero-Day Exploits, GitHub Actions Supply Chain Attacks, and OTP Auth Flaws

Comments
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.

Already have an account? Sign in
AI Agents, Jupyter Tooling, and LLM Code Gen Production Metrics

AI Agents, Jupyter Tooling, and LLM Code Gen Production Metrics

Comments
3 min read
SQLite Internals, PostgreSQL Performance & Multi-Tenancy Patterns

SQLite Internals, PostgreSQL Performance & Multi-Tenancy Patterns

Comments
3 min read
FlashAttention CUDA Kernel, Strix Halo MOE Boost, & NVIDIA DLSS 4.5 Driver Update

FlashAttention CUDA Kernel, Strix Halo MOE Boost, & NVIDIA DLSS 4.5 Driver Update

Comments
3 min read
Claude Code Access & Optimization Strategies; New LLM Response Vault for Developers

Claude Code Access & Optimization Strategies; New LLM Response Vault for Developers

Comments
3 min read
Ollama v0.30.0, Qwen3.5 35B, & 1-bit Multimodal AI on WebGPU

Ollama v0.30.0, Qwen3.5 35B, & 1-bit Multimodal AI on WebGPU

Comments
3 min read
Nginx CVE-2026-9256, AI Prompt Injection Defenses, and Claude AI Data Leak Demo

Nginx CVE-2026-9256, AI Prompt Injection Defenses, and Claude AI Data Leak Demo

Comments
4 min read
Scaling RAG for 10M+ Docs, .md Agent Memory, & Claude Code for Motion Graphics

Scaling RAG for 10M+ Docs, .md Agent Memory, & Claude Code for Motion Graphics

Comments
3 min read
DuckDB Delta, PostgreSQL 17 Migration, & SQLite Optimization Deep Dives

DuckDB Delta, PostgreSQL 17 Migration, & SQLite Optimization Deep Dives

Comments
3 min read
PatentLLM: CUDA TileLang/Triton B200 5x Speedup, RTX 5090 Power, PTX Grammar

PatentLLM: CUDA TileLang/Triton B200 5x Speedup, RTX 5090 Power, PTX Grammar

Comments
3 min read
Claude Code Deep Dive: Motion Graphics, Dev Tooling & Trending AI Repos

Claude Code Deep Dive: Motion Graphics, Dev Tooling & Trending AI Repos

Comments
3 min read
llama.cpp Checkpoint Fix, NuExtract3 VLM, & Qwen3.6 Local Inference Benchmarks

llama.cpp Checkpoint Fix, NuExtract3 VLM, & Qwen3.6 Local Inference Benchmarks

Comments
3 min read
AI Prompt Injection, Drupal SQLi Exploitation, and Nmap for Hardening

AI Prompt Injection, Drupal SQLi Exploitation, and Nmap for Hardening

Comments
3 min read
AI Agents & Python Workflows: Anthropic Skills, Jupyter Challenges, and Edge Deployment

AI Agents & Python Workflows: Anthropic Skills, Jupyter Challenges, and Edge Deployment

Comments
3 min read
SQLite Optimization, PostgreSQL Async Queries, & DuckLake Dataframe Spec

SQLite Optimization, PostgreSQL Async Queries, & DuckLake Dataframe Spec

Comments
3 min read
RTX 5080 Undervolt Benchmarks, CGO-Free CUDA API Binding, & AMD GPU Compatibility Fix

RTX 5080 Undervolt Benchmarks, CGO-Free CUDA API Binding, & AMD GPU Compatibility Fix

Comments
3 min read
Claude API Skills, Opus Token Benchmarks, & Multimodal LLM Document QA

Claude API Skills, Opus Token Benchmarks, & Multimodal LLM Document QA

Comments
3 min read
llama.cpp Native Tools, Qwen GGUF Models, and Local Multimodal Audio Tools

llama.cpp Native Tools, Qwen GGUF Models, and Local Multimodal Audio Tools

Comments
3 min read
Megalodon GitHub Supply Chain, Anthropic's Mythos AI for Vulns, & NoEyes Security Map

Megalodon GitHub Supply Chain, Anthropic's Mythos AI for Vulns, & NoEyes Security Map

Comments
2 min read
Local LLM for Claude Code, AI Workflow Orchestration, and MLOps Deployment Patterns

Local LLM for Claude Code, AI Workflow Orchestration, and MLOps Deployment Patterns

Comments
3 min read
DuckDB 1.5.2 Release, DuckLake v1.0 & PostgRESTxn for Atomic PG Transactions

DuckDB 1.5.2 Release, DuckLake v1.0 & PostgRESTxn for Atomic PG Transactions

Comments
4 min read
AMD GPU/AI Launches, Legacy Driver Update & CUDA Optimization Platform

AMD GPU/AI Launches, Legacy Driver Update & CUDA Optimization Platform

Comments
3 min read
Claude Code Deep Dive: Local LLM Integration & Developer Workflow

Claude Code Deep Dive: Local LLM Integration & Developer Workflow

Comments
3 min read
Gemma4 Apex GGUF, Ollama Context Optimization, & Llama3 Benchmarks

Gemma4 Apex GGUF, Ollama Context Optimization, & Llama3 Benchmarks

Comments
3 min read
AI Security CTF, GitHub CI/CD Supply Chain Attack, & Trend Micro Apex One Zero-Day

AI Security CTF, GitHub CI/CD Supply Chain Attack, & Trend Micro Apex One Zero-Day

1
Comments
4 min read
MCP Server LLM Orchestration, GSD-Redux Automation, & DE for AI Production

MCP Server LLM Orchestration, GSD-Redux Automation, & DE for AI Production

Comments
4 min read
DuckDB 1.5.3 Adds Quack Client-Server, SQLite Gets Cypher Graph Extension

DuckDB 1.5.3 Adds Quack Client-Server, SQLite Gets Cypher Graph Extension

Comments
3 min read
RTX 5090 Cooling, BeeLlama VRAM Opts, Resizable BAR Performance Gains

RTX 5090 Cooling, BeeLlama VRAM Opts, Resizable BAR Performance Gains

1
Comments
4 min read
NuExtract3 VLM, Claude MCP Workflows, Anthropic API Billing Shock

NuExtract3 VLM, Claude MCP Workflows, Anthropic API Billing Shock

Comments
3 min read
BeeLlama v0.2.0 boosts inference; ByteShape speeds Qwen on laptops; Llama 3.1 performance on older GPUs

BeeLlama v0.2.0 boosts inference; ByteShape speeds Qwen on laptops; Llama 3.1 performance on older GPUs

Comments
3 min read
Microsoft Defender Zero-Days, GitHub Supply Chain Breaches, and Python Package Compromises

Microsoft Defender Zero-Days, GitHub Supply Chain Breaches, and Python Package Compromises

Comments
3 min read
Applied AI: Orchestration Platforms, Airflow Integration, & Claude Code Workflows

Applied AI: Orchestration Platforms, Airflow Integration, & Claude Code Workflows

Comments
3 min read
DuckDB Lance Lakehouse Integration for Vector Search; SQLite Journaling; pgrls RLS Linter

DuckDB Lance Lakehouse Integration for Vector Search; SQLite Journaling; pgrls RLS Linter

Comments 1
3 min read
Go+CUDA Optimization, LLM VRAM Benchmarks & NVIDIA G-SYNC Firmware 1.1.6

Go+CUDA Optimization, LLM VRAM Benchmarks & NVIDIA G-SYNC Firmware 1.1.6

2
Comments
3 min read
Anthropic's Free Dev Courses, Claude Code 'Vibe Coding', & MCP Server Client for Cloud AI

Anthropic's Free Dev Courses, Claude Code 'Vibe Coding', & MCP Server Client for Cloud AI

Comments
4 min read
Qwen 3.6 & llama.cpp Push Local Inference Limits on Consumer GPUs

Qwen 3.6 & llama.cpp Push Local Inference Limits on Consumer GPUs

Comments
3 min read
GitHub Breach via VSCode Extension, ZTE Router CVE-2026-34472, & Public Repo Secrets Leaks

GitHub Breach via VSCode Extension, ZTE Router CVE-2026-34472, & Public Repo Secrets Leaks

Comments
3 min read
Applied AI: From Agent Orchestration to Workflow Automation & Code Generation

Applied AI: From Agent Orchestration to Workflow Automation & Code Generation

Comments
3 min read
SQLite Journaling on SMB, TypeGraph for SQL Graphs, Cross-Engine Migrations

SQLite Journaling on SMB, TypeGraph for SQL Graphs, Cross-Engine Migrations

Comments
3 min read
LLM Compilers, GGUF Quantization, & Radeon RX 9060 Benchmarks

LLM Compilers, GGUF Quantization, & Radeon RX 9060 Benchmarks

Comments
3 min read
Claude, OpenAI Models & AI Tooling: Strategic Shifts & Research Breakthroughs

Claude, OpenAI Models & AI Tooling: Strategic Shifts & Research Breakthroughs

Comments
3 min read
LM Studio Adds MTP Speculative Decoding; Qwen 3.6 GGUF Quants, Ollama Insights

LM Studio Adds MTP Speculative Decoding; Qwen 3.6 GGUF Quants, Ollama Insights

Comments
3 min read
NPM Supply Chain Compromise, cPanel Root RCE, AWS Pathfinding Labs

NPM Supply Chain Compromise, cPanel Root RCE, AWS Pathfinding Labs

Comments
3 min read
AI Agents Observability, Python Logging for OTel, & PySpark Code Linter

AI Agents Observability, Python Logging for OTel, & PySpark Code Linter

Comments 1
3 min read
PostgreSQL: New Time-Series Extension & Replication Monitor; DuckDB in Production

PostgreSQL: New Time-Series Extension & Replication Monitor; DuckDB in Production

Comments
3 min read
Intel Xe3P Leaks 160GB LPDDR5X; FlashAttention-2 in CuTe & Custom CUDA GPT-2 Engine

Intel Xe3P Leaks 160GB LPDDR5X; FlashAttention-2 in CuTe & Custom CUDA GPT-2 Engine

Comments
3 min read
Gemini 3.5 Flash, Claude Design, & LLM Source Reliability Insights

Gemini 3.5 Flash, Claude Design, & LLM Source Reliability Insights

Comments
3 min read
Local LLMs: Bytedance Lance 3B Multimodal, llama.cpp MTP, Ollama Client

Local LLMs: Bytedance Lance 3B Multimodal, llama.cpp MTP, Ollama Client

Comments
3 min read
Cloud Is a Luxury Car — Two Philosophies of Building Data Apps in 2026

Cloud Is a Luxury Car — Two Philosophies of Building Data Apps in 2026

Comments
8 min read
Cloudflare Tunnel as the Indie Developer's Public IP

Cloudflare Tunnel as the Indie Developer's Public IP

Comments
7 min read
The Insight-Free Property of Vendor RAGs — A Feature, Not a Bug

The Insight-Free Property of Vendor RAGs — A Feature, Not a Bug

Comments
6 min read
The `uv` Era — Disposable Python Environments and What OpenAI's Astral Acquisition Means

The `uv` Era — Disposable Python Environments and What OpenAI's Astral Acquisition Means

1
Comments
6 min read
Building a Hybrid RAG in 200 Lines — SQLite + FTS5 + sqlite-vec + RRF

Building a Hybrid RAG in 200 Lines — SQLite + FTS5 + sqlite-vec + RRF

Comments 1
6 min read
Cortex Search vs Hybrid SQLite RAG — A Cost and Latency Teardown

Cortex Search vs Hybrid SQLite RAG — A Cost and Latency Teardown

Comments 1
6 min read
Inside Streamlit's Re-Run Model — Why Hot Reload Feels Instant

Inside Streamlit's Re-Run Model — Why Hot Reload Feels Instant

Comments
6 min read
Why Snowflake's Bet on Streamlit Just Works — And Where Solo Builders Still Win

Why Snowflake's Bet on Streamlit Just Works — And Where Solo Builders Still Win

Comments
9 min read
How AI Quietly Revived Open Source — A Closing Note on the People Who Made the Pieces

How AI Quietly Revived Open Source — A Closing Note on the People Who Made the Pieces

1
Comments
9 min read
Windows MiniPlasma Zero-Day, TanStack Supply Chain Hardening & AudioHijack AI Attacks on LLMs

Windows MiniPlasma Zero-Day, TanStack Supply Chain Hardening & AudioHijack AI Attacks on LLMs

1
Comments
3 min read
AI Workflow Optimization: Snowflake Cortex, Claude Code Performance & Productivity

AI Workflow Optimization: Snowflake Cortex, Claude Code Performance & Productivity

1
Comments
3 min read
DuckDB EC2 Optimization, Postgres FDW Pushdown, SQLite NetBeans Connectivity

DuckDB EC2 Optimization, Postgres FDW Pushdown, SQLite NetBeans Connectivity

1
Comments
4 min read
loading...