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.

macOS ping OOB Write Disclosed, Grafana Mass CVE Scanner, AI Code Security Risks

macOS ping OOB Write Disclosed, Grafana Mass CVE Scanner, AI Code Security Risks

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
Optimizing LLM Workflows: Context Management, Model Comparisons, and AI-Powered Automation

Optimizing LLM Workflows: Context Management, Model Comparisons, and AI-Powered Automation

Comments
4 min read
SQLite 3.53.0 Bug, PostgreSQL Performance, New Postgres TUI

SQLite 3.53.0 Bug, PostgreSQL Performance, New Postgres TUI

Comments
3 min read
GPU Hardware & Driver Update: RTX 5090 Benchmarks, llama.cpp MTP, Windows 11 Fix

GPU Hardware & Driver Update: RTX 5090 Benchmarks, llama.cpp MTP, Windows 11 Fix

Comments
3 min read
Anthropic's Claude Gains Context Control, Excels in Frontend Dev & Agent Simulations

Anthropic's Claude Gains Context Control, Excels in Frontend Dev & Agent Simulations

Comments
3 min read
llama.cpp Optimizations & New Qwopus3.5-9B GGUF Model Boost Local AI Performance

llama.cpp Optimizations & New Qwopus3.5-9B GGUF Model Boost Local AI Performance

Comments
3 min read
Linux Kernel SSH Key Flaw, CrushFTP Yara Detection, & Vercel Typosquatting Attack

Linux Kernel SSH Key Flaw, CrushFTP Yara Detection, & Vercel Typosquatting Attack

Comments
3 min read
LLM Persistent Memory & Python Tooling Elevate AI Agent Workflows

LLM Persistent Memory & Python Tooling Elevate AI Agent Workflows

Comments
3 min read
CUDA Cutile-rs Beta, AMD FSR 4.1 Release, & Forza Horizon 6 GPU Benchmarks

CUDA Cutile-rs Beta, AMD FSR 4.1 Release, & Forza Horizon 6 GPU Benchmarks

Comments
3 min read
Claude Code Persistent Memory, Multi-Agent AI Architectures, & Model Quirks

Claude Code Persistent Memory, Multi-Agent AI Architectures, & Model Quirks

Comments
4 min read
llama.cpp MTP Boost, New Gemma-4 GGUF, & Qwen 3.6 Local Benchmarks

llama.cpp MTP Boost, New Gemma-4 GGUF, & Qwen 3.6 Local Benchmarks

Comments
3 min read
Microsoft Exchange Zero-Day, Linux Kernel LPE, and an Open-Source Docker Scanner

Microsoft Exchange Zero-Day, Linux Kernel LPE, and an Open-Source Docker Scanner

Comments
3 min read
Reel VCR for LLM APIs, AI-Generated PySpark & MacOS AI Agent Demo

Reel VCR for LLM APIs, AI-Generated PySpark & MacOS AI Agent Demo

Comments
3 min read
PostgreSQL JSON Ext., Vector Search, & SQLite Window Func Overflow

PostgreSQL JSON Ext., Vector Search, & SQLite Window Func Overflow

Comments
3 min read
Custom CUDA Kernels, Modded RTX 4090 48GB VRAM, & DLSS DLL Manager

Custom CUDA Kernels, Modded RTX 4090 48GB VRAM, & DLSS DLL Manager

BERJAYA 1
Comments
3 min read
Claude Limits Reset, Orthrus Boosts LLM Gen, Claude Mythos Cracks macOS

Claude Limits Reset, Orthrus Boosts LLM Gen, Claude Mythos Cracks macOS

Comments
4 min read
Local AI Roundup: Qwen3-8B Acceleration, Offline Gemma Robot, & Intern-S2 Multimodal

Local AI Roundup: Qwen3-8B Acceleration, Offline Gemma Robot, & Intern-S2 Multimodal

Comments
3 min read
NGINX Heap Overflow (CVE-2026-42945), BitLocker Zero-Day, & Chrome Extension Supply Chain Attack

NGINX Heap Overflow (CVE-2026-42945), BitLocker Zero-Day, & Chrome Extension Supply Chain Attack

BERJAYA 1
Comments
3 min read
LLM Engineering: Architecting Agentic RAG and Conversational BI

LLM Engineering: Architecting Agentic RAG and Conversational BI

BERJAYA 1
Comments
3 min read
PostgreSQL Benchmarking Tool & SQLite Internals: API Error Handling, Join Optimization

PostgreSQL Benchmarking Tool & SQLite Internals: API Error Handling, Join Optimization

BERJAYA 1
Comments
3 min read
RTX 5090, LLaMA.cpp TurboQuant, & Blackwell CUDA Scheduling Boosts GPU Performance

RTX 5090, LLaMA.cpp TurboQuant, & Blackwell CUDA Scheduling Boosts GPU Performance

BERJAYA 1
Comments
3 min read
Claude Code Config & Pricing Updates; GPT-5.5 Codex Benchmarks & Bedrock Cost Warning

Claude Code Config & Pricing Updates; GPT-5.5 Codex Benchmarks & Bedrock Cost Warning

BERJAYA 1
Comments
3 min read
LLaMA.cpp Gets Qwen MTP Boost, Ring-2.6-1T for Ollama, AMD GPU Fixes

LLaMA.cpp Gets Qwen MTP Boost, Ring-2.6-1T for Ollama, AMD GPU Fixes

Comments
3 min read
Win11 Zero-Days, npm Supply Chain, & AI Agent Security Threats

Win11 Zero-Days, npm Supply Chain, & AI Agent Security Threats

Comments
3 min read
Claude Code 'Run Until Done' Mode, AI Concierge, & Mythos Scan for Curl Bugs

Claude Code 'Run Until Done' Mode, AI Concierge, & Mythos Scan for Curl Bugs

Comments
3 min read
SQLite Corruption in Sandboxes, PostgreSQL Caching, & Rust DB Proxy Architecture

SQLite Corruption in Sandboxes, PostgreSQL Caching, & Rust DB Proxy Architecture

Comments
3 min read
AMD RDNA 4 & AI PRO GPUs Launch, FSR 4.1 Benchmarks, DGX Water Cooling

AMD RDNA 4 & AI PRO GPUs Launch, FSR 4.1 Benchmarks, DGX Water Cooling

Comments
3 min read
Claude Code Async /goal Mode, API Billing Warning, TabPFN-3 Model Release

Claude Code Async /goal Mode, API Billing Warning, TabPFN-3 Model Release

Comments
3 min read
llama.cpp Gains llama-eval, MagicQuant v2.0 for GGUF, Needle 26M Tool Model Released

llama.cpp Gains llama-eval, MagicQuant v2.0 for GGUF, Needle 26M Tool Model Released

Comments
4 min read
AI-Powered Zero-Days Bypass 2FA; Passkey & Git Supply Chain Attacks Explored

AI-Powered Zero-Days Bypass 2FA; Passkey & Git Supply Chain Attacks Explored

Comments
4 min read
Claude on AWS GA with Managed Agents; LLM Structured Output Robustness; DuckLake SDK for AI Data

Claude on AWS GA with Managed Agents; LLM Structured Output Robustness; DuckLake SDK for AI Data

Comments
3 min read
SQLite Encryption, DuckLake SDK for DuckDB, & PostgreSQL Git-style Branches

SQLite Encryption, DuckLake SDK for DuckDB, & PostgreSQL Git-style Branches

Comments
3 min read
RTX 5080 Launched, Rust for CUDA, & LLM GPU Scheduling Deep Dive

RTX 5080 Launched, Rust for CUDA, & LLM GPU Scheduling Deep Dive

Comments
3 min read
Cloud AI: Claude on AWS GA, Agent Payments, & LLM Stack Optimization

Cloud AI: Claude on AWS GA, Agent Payments, & LLM Stack Optimization

Comments
4 min read
ExLlamaV3 Updates, Unsloth Qwen GGUFs & Phi3 Autonomous Bridge

ExLlamaV3 Updates, Unsloth Qwen GGUFs & Phi3 Autonomous Bridge

Comments 1
3 min read
[06] Portfolio Defense Dashboard — One Screen to Rule Your Morning

[06] Portfolio Defense Dashboard — One Screen to Rule Your Morning

Comments
6 min read
Ollama Out-of-Bounds Read, Docker UFW Bypass, & EagleSpy RAT Analysis

Ollama Out-of-Bounds Read, Docker UFW Bypass, & EagleSpy RAT Analysis

Comments
4 min read
Local LLMs on Mobile, Enterprise Code Gen Workflows, & Production AI Cost Management

Local LLMs on Mobile, Enterprise Code Gen Workflows, & Production AI Cost Management

Comments
3 min read
SQLite Concurrency Corruption, DuckDB Delta Writes, and DuckLake Data Inlining

SQLite Concurrency Corruption, DuckDB Delta Writes, and DuckLake Data Inlining

Comments
3 min read
DeepSeek-V4-Flash Benchmarks, FlashRT CUDA Runtime, & V100 LLM Performance

DeepSeek-V4-Flash Benchmarks, FlashRT CUDA Runtime, & V100 LLM Performance

Comments
3 min read
Claude Code Usage Limits, Qwen 3.6 Benchmarks vs. Opus, & Mythos METR Impact

Claude Code Usage Limits, Qwen 3.6 Benchmarks vs. Opus, & Mythos METR Impact

Comments
3 min read
DeepSeek V4, `llama.cpp` Q4_K_M, & Ollama Ryzen APU Guide Boost Local LLM

DeepSeek V4, `llama.cpp` Q4_K_M, & Ollama Ryzen APU Guide Boost Local LLM

Comments
3 min read
AI-Driven Kernel LPE Discovery, ChromaDB Memory Poisoning & JDownloader Supply Chain Attack

AI-Driven Kernel LPE Discovery, ChromaDB Memory Poisoning & JDownloader Supply Chain Attack

Comments
3 min read
Scaling Workflows with Dagster & Mastering LLM Code Generation Prompts

Scaling Workflows with Dagster & Mastering LLM Code Generation Prompts

Comments
3 min read
SQLite `generate_series` Precision Bug, PostgreSQL Pagination Tuning, & Large Table Replication

SQLite `generate_series` Precision Bug, PostgreSQL Pagination Tuning, & Large Table Replication

Comments 1
3 min read
CUDA-Oxide 0.1, RTX 5070 Launch, & BeeLlama.cpp Boost 3090 Inference

CUDA-Oxide 0.1, RTX 5070 Launch, & BeeLlama.cpp Boost 3090 Inference

Comments
3 min read
Claude Code HTML Prompts & GPT-5.5 API Cost Changes Highlight Developer Focus

Claude Code HTML Prompts & GPT-5.5 API Cost Changes Highlight Developer Focus

Comments
3 min read
BeeLlama.cpp enhances llama.cpp, Qwen 35B hits 128K context, iOS local LLMs with Ollama

BeeLlama.cpp enhances llama.cpp, Qwen 35B hits 128K context, iOS local LLMs with Ollama

Comments
3 min read
Linux 'Dirty Frag' Zero-Day, Cilium CI/CD Hardening, and AI-Powered RE with pyghidra-mcp

Linux 'Dirty Frag' Zero-Day, Cilium CI/CD Hardening, and AI-Powered RE with pyghidra-mcp

Comments
3 min read
Optimizing Python AI Inference, Orchestrating Workflows, & Personalized Podcasts with Claude

Optimizing Python AI Inference, Orchestrating Workflows, & Personalized Podcasts with Claude

Comments
3 min read
PostgreSQL AI Memory, Perf Tuning; Data Pipeline Orchestration Comparison

PostgreSQL AI Memory, Perf Tuning; Data Pipeline Orchestration Comparison

Comments 1
3 min read
CUDA-Oxide 0.1 Lands; RTX 5090 Launches with 32GB & Hits 600 Tok/s

CUDA-Oxide 0.1 Lands; RTX 5090 Launches with 32GB & Hits 600 Tok/s

Comments
3 min read
Claude API Integrations, AMD Local AI Tools & Production Inference Optimization

Claude API Integrations, AMD Local AI Tools & Production Inference Optimization

Comments
4 min read
Local AI Updates: llama.cpp MTP, vLLM Gemma 4 Speeds, Ollama Coder Benchmarks

Local AI Updates: llama.cpp MTP, vLLM Gemma 4 Speeds, Ollama Coder Benchmarks

Comments
3 min read
Bitlocker Bypass, AI Trust Exploits, and FreeBSD RCE Disclosures

Bitlocker Bypass, AI Trust Exploits, and FreeBSD RCE Disclosures

Comments
4 min read
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
loading...