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.

Bitlocker Bypass, AI Trust Exploits, and FreeBSD RCE Disclosures

Bitlocker Bypass, AI Trust Exploits, and FreeBSD RCE Disclosures

Comments
4 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
Local LLM-Python Code Integration, Data Agent Gaps, & Multi-AI Creative Workflows

Local LLM-Python Code Integration, Data Agent Gaps, & Multi-AI Creative Workflows

Comments
3 min read
SQLite Internals & Audit Patterns; New Open-Source PostgreSQL UI

SQLite Internals & Audit Patterns; New Open-Source PostgreSQL UI

Comments
4 min read
AMD MI350P, CUDA WarpReduction, & Adrenalin 26.5.1 Driver Updates

AMD MI350P, CUDA WarpReduction, & Adrenalin 26.5.1 Driver Updates

Comments
3 min read
Claude API Rate Limits Boost, AI Pinball Dev Workflow, Meta's ProgramBench for Code Gen

Claude API Rate Limits Boost, AI Pinball Dev Workflow, Meta's ProgramBench for Code Gen

Comments
3 min read
llama.cpp supports Sparse MoE, new Qwen3.6 GGUF, & WebWorld for local agents

llama.cpp supports Sparse MoE, new Qwen3.6 GGUF, & WebWorld for local agents

Comments
3 min read
Maybe SQLite Is Still Better Than DuckDB for My Workloads

Maybe SQLite Is Still Better Than DuckDB for My Workloads

Comments
8 min read
New CVEs in Ollama & DAEMON Tools; Webhooks Lack Signature Checks

New CVEs in Ollama & DAEMON Tools; Webhooks Lack Signature Checks

Comments
4 min read
Gen AI Tech Stack Demand, Copilot Workflow, & Claude-Powered Automation

Gen AI Tech Stack Demand, Copilot Workflow, & Claude-Powered Automation

Comments
3 min read
SQLite CLI Prompts, PostgreSQL Load Balancing with pgkeeper, PgBouncer Tuning

SQLite CLI Prompts, PostgreSQL Load Balancing with pgkeeper, PgBouncer Tuning

Comments
3 min read
RTX 5080 Sighted, ROCm 7.2.3 Released, & AMD RDNA4 Linux Drivers Emerge

RTX 5080 Sighted, ROCm 7.2.3 Released, & AMD RDNA4 Linux Drivers Emerge

Comments
3 min read
Claude Code Integration, Token Burn Analysis & Qwen2-VL Fine-tuning Insights

Claude Code Integration, Token Burn Analysis & Qwen2-VL Fine-tuning Insights

Comments
3 min read
Gemma 4 MTP, vibevoice.cpp for Multimodal AI, & Ollama Desktop Layer for Local Deployment

Gemma 4 MTP, vibevoice.cpp for Multimodal AI, & Ollama Desktop Layer for Local Deployment

Comments
3 min read
Linux 'Copy Fail' Exploit, Acoustic Keystroke Recovery, & New Lateral Movement

Linux 'Copy Fail' Exploit, Acoustic Keystroke Recovery, & New Lateral Movement

Comments
3 min read
Async Embedding Batching, Dev Workflow AI Plugin, & LLM-Powered Game Development

Async Embedding Batching, Dev Workflow AI Plugin, & LLM-Powered Game Development

Comments
3 min read
SQLite Internals & PostgreSQL Multi-Master Replication Updates

SQLite Internals & PostgreSQL Multi-Master Replication Updates

Comments
3 min read
AMD Ryzen AI Max+ PRO 495 Leak, RTX 5080 Tease, & Interactive CUDA Lessons

AMD Ryzen AI Max+ PRO 495 Leak, RTX 5080 Tease, & Interactive CUDA Lessons

Comments
3 min read
Claude Code Plugin for Multi-Session Dev, Qwen2.5 QLoRA, & Real-Time Claude-Built Game

Claude Code Plugin for Multi-Session Dev, Qwen2.5 QLoRA, & Real-Time Claude-Built Game

Comments
3 min read
llama.cpp MTP Beta, Gemma GGUF Fixes, & Sentinel Local-First AI Coding App

llama.cpp MTP Beta, Gemma GGUF Fixes, & Sentinel Local-First AI Coding App

Comments
3 min read
[05] When to Pull the Trigger on FIRE — Monte Carlo Says You're Already Free

[05] When to Pull the Trigger on FIRE — Monte Carlo Says You're Already Free

Comments
5 min read
[04] The 90/10 Portfolio — Dividend Core + Growth Satellite with a Live Simulator

[04] The 90/10 Portfolio — Dividend Core + Growth Satellite with a Live Simulator

Comments
3 min read
[03] Designing a Personal Commitment Line — Two Loans, One Defense System

[03] Designing a Personal Commitment Line — Two Loans, One Defense System

Comments
5 min read
[02] Stress Testing Your Life — What Happens at -30%, -50%, -60%?

[02] Stress Testing Your Life — What Happens at -30%, -50%, -60%?

Comments
5 min read
CopyFail Linux Root, cPanel Auth Bypass, & Numeric Data Exfil Techniques

CopyFail Linux Root, cPanel Auth Bypass, & Numeric Data Exfil Techniques

Comments
3 min read
Code RAG for AI Agents, Practical Vector DB Building, and PyTorch Lightning Security Alert

Code RAG for AI Agents, Practical Vector DB Building, and PyTorch Lightning Security Alert

Comments
4 min read
RTX 3090 vLLM Local LLM Speeds, NVIDIA NIM Inconsistencies, AMD Mesa Driver Plan

RTX 3090 vLLM Local LLM Speeds, NVIDIA NIM Inconsistencies, AMD Mesa Driver Plan

Comments
3 min read
Cloud AI Developer Deep Dive: Claude Code Utilities & Gemini 3 Gaming

Cloud AI Developer Deep Dive: Claude Code Utilities & Gemini 3 Gaming

Comments
3 min read
Qwen3.6-27B Local Inference on RTX 3090 with Native vLLM & Ollama Fallback

Qwen3.6-27B Local Inference on RTX 3090 with Native vLLM & Ollama Fallback

Comments
3 min read
CopyFail Linux Root, AI Jailbreak & Emerging AI Security Platforms

CopyFail Linux Root, AI Jailbreak & Emerging AI Security Platforms

Comments
3 min read
Local LLMs with PandasAI, Claude for Code Security & Jupyter Integration

Local LLMs with PandasAI, Claude for Code Security & Jupyter Integration

Comments
3 min read
DuckDB 1.5.1, MacBook Benchmarks, & Browser-based Postgres Workspace

DuckDB 1.5.1, MacBook Benchmarks, & Browser-based Postgres Workspace

Comments
3 min read
PFlash VRAM Optimization, NVIDIA 5090 NVFP4 Benchmarks, AMD HDMI 2.1 Linux Drivers

PFlash VRAM Optimization, NVIDIA 5090 NVFP4 Benchmarks, AMD HDMI 2.1 Linux Drivers

Comments
4 min read
Claude Security Beta, Opus 4.7 Regression, & LLM Cost-Saving Router for Devs

Claude Security Beta, Opus 4.7 Regression, & LLM Cost-Saving Router for Devs

Comments
3 min read
PFlash Boosts llama.cpp Prefill; Ollama Sees Major Speed Gains; Llama 3.2 on Android

PFlash Boosts llama.cpp Prefill; Ollama Sees Major Speed Gains; Llama 3.2 on Android

Comments
3 min read
Linux Root Exploit (CVE-2026-31431), SAP npm Supply Chain Attack, & Homelab Secrets with Infisical

Linux Root Exploit (CVE-2026-31431), SAP npm Supply Chain Attack, & Homelab Secrets with Infisical

Comments
2 min read
AI Agent Orchestration & Applied LLMs: Code Search, Workflow Optimization, Document Processing

AI Agent Orchestration & Applied LLMs: Code Search, Workflow Optimization, Document Processing

Comments
3 min read
SQLite Formal Verification, Postgres FTS with ParadeDB, & Multi-DB Schema Diff

SQLite Formal Verification, Postgres FTS with ParadeDB, & Multi-DB Schema Diff

Comments
3 min read
GPU Hardware, VRAM Optimization & Next-Gen Driver Updates

GPU Hardware, VRAM Optimization & Next-Gen Driver Updates

1
Comments
3 min read
Claude Connectors Expand, New Open-Source Claude Code MCP, and Real-time AI Pricing Trackers

Claude Connectors Expand, New Open-Source Claude Code MCP, and Real-time AI Pricing Trackers

Comments
3 min read
Qwen 3.5 SAEs & 3.6 Q6_K Multimodal, DeepSeek's Visual Primitives Framework

Qwen 3.5 SAEs & 3.6 Q6_K Multimodal, DeepSeek's Visual Primitives Framework

Comments
3 min read
CVE-2026-41940, Supply Chain Defense & Linux Root Exploit

CVE-2026-41940, Supply Chain Defense & Linux Root Exploit

Comments
3 min read
LLMs for Workflow Automation, Agent Orchestration & Enhanced Code Review

LLMs for Workflow Automation, Agent Orchestration & Enhanced Code Review

Comments
3 min read
DuckDB 1.5.2, PostgreSQL Linux 7.0 Regression, & SQLite Formal Verification

DuckDB 1.5.2, PostgreSQL Linux 7.0 Regression, & SQLite Formal Verification

Comments
3 min read
FlashQLA Kernels Accelerate AI; NVIDIA & AMD Unveil New GPUs

FlashQLA Kernels Accelerate AI; NVIDIA & AMD Unveil New GPUs

Comments
3 min read
Gemini Deep Research Max, Claude API Warm-Caching, & Blender MCP Connector

Gemini Deep Research Max, Claude API Warm-Caching, & Blender MCP Connector

Comments
3 min read
Mistral Medium 3.5 GGUF, FlashQLA Boost for Qwen, & Ollama Playground

Mistral Medium 3.5 GGUF, FlashQLA Boost for Qwen, & Ollama Playground

Comments
3 min read
Critical RCEs in Microsoft AI & GitHub, plus CrowdSec for Hardening

Critical RCEs in Microsoft AI & GitHub, plus CrowdSec for Hardening

Comments
3 min read
Optimizing LLM Workflows: Claude for Evaluation, Blender Integration & Token Efficiency

Optimizing LLM Workflows: Claude for Evaluation, Blender Integration & Token Efficiency

Comments
3 min read
PostgreSQL Extension for Row Padding, pgBackRest EOL, and SQLite Windows XP Support

PostgreSQL Extension for Row Padding, pgBackRest EOL, and SQLite Windows XP Support

Comments
3 min read
NVIDIA RTX 5070 Laptop GPU Launches; AMD Preps AI Scheduler; Qwen GGUF Benchmarks

NVIDIA RTX 5070 Laptop GPU Launches; AMD Preps AI Scheduler; Qwen GGUF Benchmarks

Comments
3 min read
Claude AI Dev Tools: MCP Server, Blender Connector & Sonnet Evaluation Patterns

Claude AI Dev Tools: MCP Server, Blender Connector & Sonnet Evaluation Patterns

Comments
3 min read
Local LLMs & Multimodal: Qwen GGUF, Nemotron-3-Nano-Omni, MiMo V2.5-Pro Released

Local LLMs & Multimodal: Qwen GGUF, Nemotron-3-Nano-Omni, MiMo V2.5-Pro Released

Comments
3 min read
Windows RPC Privilege Escalation, AI Supply Chain Breach, & Minecraft Auditing Tool

Windows RPC Privilege Escalation, AI Supply Chain Breach, & Minecraft Auditing Tool

Comments
3 min read
RAG Accessibility, AI Agent Security Testing, & Vector Search Optimization

RAG Accessibility, AI Agent Security Testing, & Vector Search Optimization

Comments
3 min read
SQLite Verification, pg_savior, & PostgreSQL Restore Strategies

SQLite Verification, pg_savior, & PostgreSQL Restore Strategies

Comments
3 min read
CUDA & VRAM Optimization Shine: Custom Kernels, DFlash Throughput, Single-GPU LLM Arch

CUDA & VRAM Optimization Shine: Custom Kernels, DFlash Throughput, Single-GPU LLM Arch

Comments
2 min read
Claude API Pricing Hikes, Code Model Configs, & Opus 4.6 Vulnerability Discovery

Claude API Pricing Hikes, Code Model Configs, & Opus 4.6 Vulnerability Discovery

1
Comments 1
3 min read
Local LLM Acceleration, Framework Comparisons, & Ollama Observability

Local LLM Acceleration, Framework Comparisons, & Ollama Observability

1
Comments
4 min read
AI SOC Evasion, Tamper-Evident AI Audits, & Bell HomeHub 3000 DoS

AI SOC Evasion, Tamper-Evident AI Audits, & Bell HomeHub 3000 DoS

Comments
3 min read
Cloudflare Boosts AI Agent Governance; Claude Model Choice & Advanced NLP

Cloudflare Boosts AI Agent Governance; Claude Model Choice & Advanced NLP

Comments
3 min read
loading...