Author

Owen Park

AI security researcher

Covers AI application security, model risk, and agentic system abuse.

ai-securityresearchapplication-security

Coverage by Owen Park (28)

Infographic showing DeepSeek V4.1 Flash served across three DGX Spark nodes with key throughput figures

Run DeepSeek V4.1 Flash on Three DGX Sparks

A stability-first SGLang deployment serves DeepSeek V4.1 Flash across three NVIDIA DGX Sparks: 750k KV cache, ~1600 tok/s prefill, ~38 tok/s single-stream decode.

Infographic mapping one to four NVIDIA DGX Sparks to the recommended local model at each node count: Qwen3.8 Flash Next, DeepSeek V4 Flash, GLM-5.3 Flash, DeepSeek V4.1 Flash.

Nvidia Dgx Spark AI Security

Best Local AI Models to Run on Your DGX Sparks

From one Spark to four: the open-weight model to serve at each node count, with measured decode, prefill and context figures from Mia's AI Lab recipes.

Data-poster diagramming an AI agent control plane: an agent routed through interception, workload identity, a policy engine and guard models to a credential broker, an MCP server and a signed audit ledger.

Agent Control Plane AI Security

The Agent Control Plane: Engineering Runtime Authorization for MCP and AI Tool Calls

Prompt injection resists a model-layer fix. Inside the agent control plane: workload identity, brokered credentials and blast-radius caps at the tool call.

ThreatFrontier poster showing Claude Code internals as a local agent runtime with tools permissions sessions and SDK

Claude Code AI Security

How Claude Code Works Internally: From CLI Startup to Agentic Tool Execution

A practical systems-level explanation of Claude Code as a local agent runtime, covering startup, authentication, tools, permissions, sessions, MCP, plugins, and the Agent SDK.

ThreatFrontier poster showing Langflow CVE-2026-33017 public workflow build endpoint remote code execution

AI Gateway Security AI Security

Critical Langflow Vulnerability Exposes AI Workflows and API Keys to Active Exploitation

CVE-2026-33017 exposes Langflow AI workflow builders to unauthenticated remote code execution through the public flow build endpoint.

Protocol schematic poster for a 128GB Apple Silicon local AI stack led by Qwen3.6

Local AI AI Security

Best Open-Weight AI Models for a 128GB Apple Silicon Mac in 2026: Qwen3.6 Leads the Pack

Qwen3.6-35B-A3B leads 2026 open-weight AI picks for 128GB Apple Silicon Macs, balancing coding, reasoning, long context and local speed for developers.

Open-weight AI model fit guide for a 24GB Apple Silicon Mac in 2026

Local AI AI Security

Best Open-Weight AI Models for a 24GB Apple Silicon Mac in 2026

Qwen3.6-27B in Q4_K_M-class quantization is the practical pick for a 24GB Apple Silicon Mac, with Gemma 4 26B A4B, Devstral Small 2 and Phi-4-mini filling specialized roles.

Claude Code versus OpenAI Codex 100 and 200 plan usage limits comparison

AI Coding Tools AI Security

Claude Code vs OpenAI Codex Limits: Which $100 or $200 Plan Is Better for Developers?

Claude Code and OpenAI Codex both offer $100 and $200 developer plans, but Codex gives clearer published limits while Claude remains stronger for reasoning-heavy coding workflows.

Desks covered

AI Security Research

Latest

Sep 12, 2026, 12:37 PM EDT · Research · Mlx12 minMLX vs llama.cpp on Apple Silicon: Which Local LLM Runtime to Actually Use

One is a portable inference engine, the other an array framework that also trains — and that single difference settles almost every practical question.

Sep 12, 2026, 12:37 PM EDT · Operations · Llm Evaluation14 minHow to Build an LLM Evaluation Harness That Catches Real Regressions

Public benchmarks only shortlist a model; your own cases decide whether to ship it. Here is the dataset, the scorers and the CI gates that catch real drift.

Sep 12, 2026, 12:37 PM EDT · Research · Prompt Caching11 minPrompt Caching Explained: Cutting Agent Costs Without Touching the Model

Your agent re-sends the same long prefix on every step and pays to recompute it. Here is the KV mechanism, the ordering rule it forces, and the break-even math.

Sep 12, 2026, 12:37 PM EDT · Research · Speculative Decoding11 minSpeculative Decoding and Multi-Token Prediction: How LLMs Generate Faster

Decode is memory-bound, so checking several tokens in one pass is nearly free. Here is the mechanism, the arithmetic behind it, and why quality never moves.