DevLog & Showcase
Hi, I’m Sergey. I build reliable AI systems and maintainable web platforms.
AI and backend engineer working with local LLMs, coding agents, model evaluation, Python, PHP, Node.js, and WordPress.
I focus on explicit contracts, reproducible evaluation, observable runtime behavior, and tools that work beyond a demo.
Latest posts
Notes on WordPress, modern stacks, and experiments in development.

Thinking vs. No-Thinking in Local LLM Agents: Five Models, Two Trials, and No Universal Winner
Five local model artifacts tested twice with and without thinking, followed by GSM8K, MMLU, and IFEval: quality, safety, latency, and deployment trade-offs.

Six Local Models on Tool-Eval-Bench: Tool Calling, Safety, and State
Six quantized local models across 69 deterministic tool-calling scenarios, with observed quality, safety, state handling, latency, token use, and explicit limitations.
Read more about Six Local Models on Tool-Eval-Bench: Tool Calling, Safety, and State

Eight Quantized Local Models on Aider Polyglot: An Operational Snapshot
Eight quantized local models across 225 Aider Polyglot tasks, with observed Pass@2, protocol failures, wall time, token use, and explicit serving confounders.
Read more about Eight Quantized Local Models on Aider Polyglot: An Operational Snapshot

Debugging Local LLM Benchmarks: Aider, llama.cpp, and Runaway Output
A practical account of building a fair local-agent benchmark, debugging reasoning-model serving, fixing greedy-decoding loops, and adding an exact-repetition circuit breaker to llama.cpp.
Read more about Debugging Local LLM Benchmarks: Aider, llama.cpp, and Runaway Output

From “No Docker” to “Trust Boundaries”: How an AUR Supply-Chain Attack Changed My View of Local Development Environments
A few months ago I wrote an article describing my local PHP and WordPress development setup on Arch Linux. The idea was simple: one command → working project No Docker.No containers.No extra abstraction layers. Just native Linux services: For a long time it worked exactly as intended. Fast.Simple.Predictable. I still believe the technical solution itself…

Zero-config local PHP/WordPress development environment on Arch Linux (without Docker)
• One nginx config • One SSL certificate • Dynamic project routing • One command project bootstrap Result: new PHP project in ~5 seconds.