https://www.danilchenko.dev/Recent content in Home on danilchenko.devHugoen-usSat, 17 Oct 2026 08:27:05 +0000https://www.danilchenko.dev/posts/ai-agent-protocols/Sun, 04 Oct 2026 08:43:24 +0000https://www.danilchenko.dev/posts/ai-agent-protocols/MCP vs A2A vs ACP vs WebMCP in 2026: which layer each agent protocol connects, what the July 2026 MCP spec changed, the security gaps, and a reading order.https://www.danilchenko.dev/posts/best-ai-models-coding-2026/Mon, 07 Sep 2026 08:41:30 +0000https://www.danilchenko.dev/posts/best-ai-models-coding-2026/The best AI models for coding in 2026 by tier: frontier, open-weight and budget, with real prices, benchmark caveats, and which one to actually use.https://www.danilchenko.dev/posts/modern-go-2026/Fri, 24 Jul 2026 08:50:31 +0000https://www.danilchenko.dev/posts/modern-go-2026/A field guide to modern Go in 2026: iterators, generic methods, Green Tea GC, JSON v2, and where Go still beats Rust for real backend and AI agent work.https://www.danilchenko.dev/posts/python-tooling-guide/Thu, 02 Jul 2026 06:00:00 +0000https://www.danilchenko.dev/posts/python-tooling-guide/A complete guide to modern Python tooling in 2026: uv, Poetry, and pip; mypy, Pyright, ty, and Pyrefly; plus free-threading, t-strings, and Polars vs Pandas.https://www.danilchenko.dev/posts/tech-careers-ai-guide/Thu, 04 Jun 2026 08:44:59 +0000https://www.danilchenko.dev/posts/tech-careers-ai-guide/9 deep dives into the 2026 tech job market: layoffs, AI displacement data, salary benchmarks from Cyprus to the US, and the productivity paradox. Full guide.https://www.danilchenko.dev/posts/llm-inference-efficiency-guide/Wed, 13 May 2026 08:55:00 +0000https://www.danilchenko.dev/posts/llm-inference-efficiency-guide/Five approaches to making LLMs faster and cheaper — compression, diffusion decoding, architecture, KV cache, and sparse attention — explained with real numbers.https://www.danilchenko.dev/posts/ai-coding-tools-guide/Mon, 13 Apr 2026 07:00:00 +0000https://www.danilchenko.dev/posts/ai-coding-tools-guide/Everything we've covered on AI coding tools — comparisons, pricing, privacy, agents, and the security risks nobody expected. Updated April 2026.https://www.danilchenko.dev/posts/software-engineer-jobs-europe/Wed, 14 Oct 2026 08:21:36 +0000https://www.danilchenko.dev/posts/software-engineer-jobs-europe/Software engineer jobs in Europe 2026: Eurostat shows ICT vacancies halved since 2022 while Cyprus and Portugal grew. Where to apply and which visa fits.https://www.danilchenko.dev/posts/ai-carb-counting-accuracy/Thu, 08 Oct 2026 08:56:25 +0000https://www.danilchenko.dev/posts/ai-carb-counting-accuracy/AI carb counting accuracy, measured: Soba got 68.5% of meals within 10 g on 400 research photos. Where it fails, what fixes it, and how 8 LLMs compared.https://www.danilchenko.dev/posts/eu-pay-transparency/Wed, 30 Sep 2026 08:19:44 +0000https://www.danilchenko.dev/posts/eu-pay-transparency/The EU Pay Transparency Directive deadline passed in June 2026, yet only 5 countries have transposed it. What developers can demand now, country by country.https://www.danilchenko.dev/how-this-blog-is-made/Sun, 27 Sep 2026 00:00:00 +0000https://www.danilchenko.dev/how-this-blog-is-made/How articles on danilchenko.dev are researched, written, checked and corrected, including the role AI plays.https://www.danilchenko.dev/posts/vibe-coding/Fri, 25 Sep 2026 08:22:42 +0000https://www.danilchenko.dev/posts/vibe-coding/Vibe coding in 2026, from someone who ships vibe-coded mini-apps: where it saves real time, where it quietly breaks in production, and an honest verdict.https://www.danilchenko.dev/posts/python-sampling-profiler/Tue, 22 Sep 2026 08:20:28 +0000https://www.danilchenko.dev/posts/python-sampling-profiler/Python 3.15's built-in sampling profiler (Tachyon) attaches to a running process by PID, no code changes. Hands-on: attach, flamegraph, wall vs CPU vs GIL.https://www.danilchenko.dev/posts/sqlc-vs-gorm-vs-ent/Mon, 14 Sep 2026 08:20:35 +0000https://www.danilchenko.dev/posts/sqlc-vs-gorm-vs-ent/sqlc vs GORM vs Ent for Go database access in 2026: type safety, real benchmark numbers, migrations, and which library actually fits your next project.https://www.danilchenko.dev/posts/ruff-vs-flake8-vs-black/Mon, 07 Sep 2026 08:21:23 +0000https://www.danilchenko.dev/posts/ruff-vs-flake8-vs-black/Ruff vs Flake8, Black, and Pylint in 2026: Astral's speed numbers, what it replaces, where it still loses, and a migration you can finish in an afternoon.https://www.danilchenko.dev/posts/food-recognition-llm/Sat, 29 Aug 2026 07:32:10 +0000https://www.danilchenko.dev/posts/food-recognition-llm/How I picked an LLM for food photo recognition in soba: a benchmark, a live A/B that cut scan cost to $0.005, and the prompt work that fixes portion weight.https://www.danilchenko.dev/posts/duckdb-python/Thu, 27 Aug 2026 08:20:56 +0000https://www.danilchenko.dev/posts/duckdb-python/DuckDB in Python turns SQL into a zero-setup analytics engine: query CSV, Parquet, and Pandas DataFrames in-process, join across sources, and add UDFs.https://www.danilchenko.dev/posts/faster-than-dijkstra/Thu, 13 Aug 2026 08:24:11 +0000https://www.danilchenko.dev/posts/faster-than-dijkstra/A new shortest path algorithm finally beats Dijkstra on sparse graphs. How it breaks the 65-year sorting barrier, and why Dijkstra still wins in practice.https://www.danilchenko.dev/posts/uv-workspaces-monorepo/Thu, 30 Jul 2026 08:22:24 +0000https://www.danilchenko.dev/posts/uv-workspaces-monorepo/Build a Python monorepo with uv workspaces: one shared lockfile and virtualenv, cross-package imports, per-package builds, and the gotchas to watch for.https://www.danilchenko.dev/posts/context-engineering/Tue, 28 Jul 2026 08:23:21 +0000https://www.danilchenko.dev/posts/context-engineering/Context engineering explained: why long-running AI agents suffer context rot, what 2026 research shows about pruning and compaction, plus a Python demo.https://www.danilchenko.dev/posts/go-cli-frameworks/Mon, 27 Jul 2026 08:21:00 +0000https://www.danilchenko.dev/posts/go-cli-frameworks/Go CLI framework showdown for 2026: Cobra vs urfave/cli vs Bubble Tea. Real code, boilerplate counts, and when to reach for each, after building all three.https://www.danilchenko.dev/posts/langgraph-vs-crewai/Sat, 25 Jul 2026 08:27:28 +0000https://www.danilchenko.dev/posts/langgraph-vs-crewai/LangGraph vs CrewAI vs OpenAI Agents SDK compared for 2026: architecture, real code, pricing, and which multi-agent framework to pick for production work.https://www.danilchenko.dev/posts/python-lazy-imports/Fri, 24 Jul 2026 08:26:17 +0000https://www.danilchenko.dev/posts/python-lazy-imports/Python lazy imports (PEP 810) land in Python 3.15. I benchmarked boto3, requests and pydantic startup: the real speedup, and how to get most of it today.https://www.danilchenko.dev/posts/eu-ai-act-delay/Thu, 23 Jul 2026 08:22:21 +0000https://www.danilchenko.dev/posts/eu-ai-act-delay/EU AI Act timeline for developers after the Digital Omnibus: what is already in force, what lands in Dec 2026, Dec 2027 and Aug 2028, and what to build now.https://www.danilchenko.dev/posts/europe-developer-salary-2026/Mon, 20 Jul 2026 08:22:44 +0000https://www.danilchenko.dev/posts/europe-developer-salary-2026/Software engineer salary in Europe for 2026, country by country: from €120K in Zurich to €30K in Bucharest, and why net pay beats the US gap you'd expect.https://www.danilchenko.dev/posts/go-json-v2/Sun, 19 Jul 2026 08:24:00 +0000https://www.danilchenko.dev/posts/go-json-v2/Go's encoding/json/v2 is a reported 2–10x faster at unmarshaling but flips v1 defaults: duplicate keys, nil slices, case matching. How to enable it and migrate.https://www.danilchenko.dev/posts/msgspec-vs-pydantic/Tue, 14 Jul 2026 08:23:57 +0000https://www.danilchenko.dev/posts/msgspec-vs-pydantic/msgspec vs Pydantic v2 in 2026: real code, reported benchmark numbers, where the speed gap actually shows up in a Python API, and how to run both together.https://www.danilchenko.dev/posts/go-ai-agent/Mon, 13 Jul 2026 08:21:59 +0000https://www.danilchenko.dev/posts/go-ai-agent/Build an AI agent in Go from scratch: a tool-calling loop against the Anthropic API in ~120 lines, no frameworks, with real code and the gotchas to watch for.https://www.danilchenko.dev/posts/django-bolt/Sat, 11 Jul 2026 08:23:30 +0000https://www.danilchenko.dev/posts/django-bolt/Django-Bolt puts Actix and Rust under Django to hit 188K RPS. I dug through the source and benchmarks — where it beats FastAPI, and where the speed evaporates.https://www.danilchenko.dev/posts/python-3-15/Fri, 10 Jul 2026 08:23:56 +0000https://www.danilchenko.dev/posts/python-3-15/Python 3.15 lands lazy imports, a frozendict builtin, unpacking in comprehensions, and the Tachyon sampling profiler. Here's what changed and what to test.https://www.danilchenko.dev/posts/fastapi-vs-litestar/Thu, 09 Jul 2026 08:22:01 +0000https://www.danilchenko.dev/posts/fastapi-vs-litestar/FastAPI vs Litestar vs Django Ninja in 2026: real code, serialization speed, dependency injection, and a clear pick for every kind of Python API project.https://www.danilchenko.dev/posts/cs-degree-worth-it/Wed, 08 Jul 2026 08:22:44 +0000https://www.danilchenko.dev/posts/cs-degree-worth-it/Is a computer science degree worth it in 2026? CS grad unemployment hit 6.1%, yet the answer flips depending on whether you study in the US or the EU.https://www.danilchenko.dev/posts/claude-sonnet-5-review/Tue, 07 Jul 2026 08:22:27 +0000https://www.danilchenko.dev/posts/claude-sonnet-5-review/Claude Sonnet 5 review: it nearly matches Opus 4.8 on coding, beats it on Terminal-Bench, and runs at just $2/$10 — but the tokenizer bites.https://www.danilchenko.dev/posts/duckdb-vs-polars/Fri, 03 Jul 2026 08:23:13 +0000https://www.danilchenko.dev/posts/duckdb-vs-polars/DuckDB vs Polars for data engineering in 2026: benchmarks, memory usage, SQL vs DataFrame ergonomics, and when to reach for each. Real numbers, honest verdict.https://www.danilchenko.dev/posts/go-generic-methods/Thu, 02 Jul 2026 08:21:35 +0000https://www.danilchenko.dev/posts/go-generic-methods/Go 1.27 finally adds generic methods: type parameters on methods at last. A hands-on tutorial on the syntax, the chaining it enables, and the interface catch.https://www.danilchenko.dev/posts/mem0-vs-cognee-vs-letta/Wed, 01 Jul 2026 08:23:14 +0000https://www.danilchenko.dev/posts/mem0-vs-cognee-vs-letta/Mem0 adds drop-in memory in 5 lines. Cognee builds a knowledge graph. Letta makes the agent its own memory. Here's which one fits your stack.https://www.danilchenko.dev/posts/perplexity-bumblebee-review/Mon, 29 Jun 2026 08:22:13 +0000https://www.danilchenko.dev/posts/perplexity-bumblebee-review/Bumblebee scans npm, PyPI, Go, MCP configs and editor extensions for compromised packages without running install scripts. What it catches, where it fits.https://www.danilchenko.dev/posts/mistral-ocr-4-tutorial/Thu, 25 Jun 2026 08:24:28 +0000https://www.danilchenko.dev/posts/mistral-ocr-4-tutorial/Extract text, tables, and structured JSON from PDFs using Mistral OCR 4 in Python. Bounding boxes, confidence scores, and a complete invoice pipeline.https://www.danilchenko.dev/posts/claude-code-workflows/Wed, 24 Jun 2026 08:24:44 +0000https://www.danilchenko.dev/posts/claude-code-workflows/Learn to build 4 real Claude Code workflow scripts for code audit, migration, security review, and research. Includes actual output and cost breakdowns.https://www.danilchenko.dev/posts/ai-layoffs-2026/Mon, 22 Jun 2026 08:24:39 +0000https://www.danilchenko.dev/posts/ai-layoffs-2026/185K tech workers cut in 2026, 1,115 per day. Gartner surveyed 350 execs and found zero ROI correlation. Deutsche Bank calls it AI redundancy washing.https://www.danilchenko.dev/posts/stanford-ai-index-2026/Sat, 20 Jun 2026 08:22:14 +0000https://www.danilchenko.dev/posts/stanford-ai-index-2026/Stanford's AI Index 2026: SWE-bench hit 100%, entry-level dev jobs down 20%, $581B invested, US-China gap at 2.7%. 12 findings, broken down.https://www.danilchenko.dev/posts/glm-5-2-review/Thu, 18 Jun 2026 08:25:00 +0000https://www.danilchenko.dev/posts/glm-5-2-review/GLM-5.2 scores 62.1 on SWE-bench Pro vs GPT-5.5's 58.6, ships under MIT, and costs $1.40/M input tokens. Benchmarks, pricing, and the China data question.https://www.danilchenko.dev/posts/litellm-vulnerability/Wed, 17 Jun 2026 08:32:06 +0000https://www.danilchenko.dev/posts/litellm-vulnerability/Six LiteLLM vulnerabilities hit in 2026, including a CVSS 10.0 RCE CISA flagged as actively exploited. Which versions are exposed and how to patch to v1.83.14+.https://www.danilchenko.dev/posts/rust-vs-go/Tue, 16 Jun 2026 08:23:54 +0000https://www.danilchenko.dev/posts/rust-vs-go/Rust vs Go for backends in 2026: where Rust's speed and memory edge is real, why Go still ships faster, and fresh HN hiring data where Rust now matches Go.https://www.danilchenko.dev/posts/go-1-26-features/Sun, 14 Jun 2026 08:22:06 +0000https://www.danilchenko.dev/posts/go-1-26-features/Go 1.26 features with code: Green Tea GC on by default (10-40% less GC overhead), new(expr), SIMD, runtime/secret, go fix, plus what changed in Go 1.27.https://www.danilchenko.dev/posts/claude-code-max-vs-pro/Sat, 13 Jun 2026 08:24:01 +0000https://www.danilchenko.dev/posts/claude-code-max-vs-pro/Claude Code Pro is $20/mo, Max 5x $100, Max 20x $200. The June 15 billing split never happened, but Max now adds $100-200 in API credits plus Fable access.https://www.danilchenko.dev/posts/claude-fable-5-review/Thu, 11 Jun 2026 08:22:24 +0000https://www.danilchenko.dev/posts/claude-fable-5-review/Claude Fable 5 hits 80.3% SWE-bench Pro and 29.3% FrontierCode Diamond. It also costs 2x Opus 4.8, retains your data 30 days, and silently falls back.https://www.danilchenko.dev/posts/gemini-flash-vs-haiku/Wed, 10 Jun 2026 08:21:45 +0000https://www.danilchenko.dev/posts/gemini-flash-vs-haiku/Gemini 3.5 Flash vs Claude Haiku 4.5 vs MAI-Code-1-Flash — SWE-bench scores, token costs, and which flash model actually writes better code in 2026.https://www.danilchenko.dev/posts/opencode-vs-claude-code/Tue, 09 Jun 2026 08:22:00 +0000https://www.danilchenko.dev/posts/opencode-vs-claude-code/OpenCode (free, 75+ models) vs Claude Code ($20/mo, best SWE-bench) vs Cursor ($20/mo, IDE-native). Real pricing, benchmarks, and which one wins for your stack.https://www.danilchenko.dev/posts/devin-desktop-review/Sat, 06 Jun 2026 08:22:38 +0000https://www.danilchenko.dev/posts/devin-desktop-review/Devin Desktop is Windsurf rebranded by Cognition: an Agent Command Center, Devin Local in place of Cascade, ACP support, and Free, $20 and $200 plans.https://www.danilchenko.dev/posts/project-glasswing/Fri, 05 Jun 2026 08:21:57 +0000https://www.danilchenko.dev/posts/project-glasswing/Project Glasswing gave Claude Mythos to 200+ orgs; it flagged 10,000 critical bugs in 8 weeks at a 90.6% true-positive rate. Why Anthropic keeps it locked.https://www.danilchenko.dev/posts/agent-client-protocol/Thu, 04 Jun 2026 08:23:11 +0000https://www.danilchenko.dev/posts/agent-client-protocol/Agent Client Protocol is LSP for AI agents: one config runs Claude Code, Gemini, or Codex in JetBrains, Zed & Neovim. Hands-on setup for JetBrains and Zed.https://www.danilchenko.dev/posts/ai-replacing-junior-developers/Wed, 03 Jun 2026 08:23:47 +0000https://www.danilchenko.dev/posts/ai-replacing-junior-developers/Junior developer employment fell 20% since 2024 while ML engineer openings surged 59%. Stanford, BLS, and Forrester data on who's being cut and what works.https://www.danilchenko.dev/posts/uv-python-tutorial/Tue, 02 Jun 2026 08:17:14 +0000https://www.danilchenko.dev/posts/uv-python-tutorial/Step-by-step uv tutorial: create a real Python CLI project, manage deps, run tests, lint with ruff, build a wheel, and ship it in Docker — from scratch.https://www.danilchenko.dev/posts/copilot-ai-credits/Mon, 01 Jun 2026 08:22:06 +0000https://www.danilchenko.dev/posts/copilot-ai-credits/A GitHub Copilot AI credit costs $0.01: 8,333 output tokens on GPT-5.6 Luna, 500 on Sol. Per-model token math, plan credit pools, and the Oct 19 model swap.https://www.danilchenko.dev/posts/claude-code-hooks/Sun, 31 May 2026 08:21:09 +0000https://www.danilchenko.dev/posts/claude-code-hooks/Build 5 real Claude Code hooks step by step — auto-format, command blocker, AI linter, test runner, and context injector. Full configs and scripts included.https://www.danilchenko.dev/posts/swe-job-market-2026/Thu, 28 May 2026 08:21:06 +0000https://www.danilchenko.dev/posts/swe-job-market-2026/ML engineer roles up 59% from 2020, general SWE openings down 49%. Dice, CompTIA, and BLS data shows a 2026 market split by AI fluency. Salaries included.https://www.danilchenko.dev/posts/webmcp-tutorial/Wed, 27 May 2026 08:20:52 +0000https://www.danilchenko.dev/posts/webmcp-tutorial/WebMCP lets AI agents call your site's forms and JS functions directly, no screen-scraping. Full working code for both APIs on the Chrome 149 origin trial.https://www.danilchenko.dev/posts/pyrefly-vs-mypy-vs-ty/Sun, 24 May 2026 08:22:48 +0000https://www.danilchenko.dev/posts/pyrefly-vs-mypy-vs-ty/Pyrefly 1.0 checks 1.85M lines/sec with 87.8% conformance, mypy 2.0 adds parallelism, ty hits sub-10ms updates. Full benchmarks and migration guide.https://www.danilchenko.dev/posts/efficient-llm-reasoning/Sat, 23 May 2026 08:23:44 +0000https://www.danilchenko.dev/posts/efficient-llm-reasoning/Seven papers fix LLM overthinking: Sketch-of-Thought cuts tokens 84%, shorter chains boost accuracy 34.5%, and budget-aware prompting halves costs.https://www.danilchenko.dev/posts/google-jules-review/Fri, 22 May 2026 08:21:56 +0000https://www.danilchenko.dev/posts/google-jules-review/Google Jules queues coding tasks, runs them in a cloud VM, and opens PRs while you sleep. Free tier gives 15 tasks/day. Here's what worked and what didn't.https://www.danilchenko.dev/posts/antigravity-cli-vs-claude-code/Thu, 21 May 2026 08:23:55 +0000https://www.danilchenko.dev/posts/antigravity-cli-vs-claude-code/Antigravity CLI vs Claude Code vs Codex CLI after 3 months: Google's rate limits still trigger 7-day lockouts, Claude Code wins on quality, Codex on cost.https://www.danilchenko.dev/posts/ai-bug-bounty-crisis/Wed, 20 May 2026 08:20:45 +0000https://www.danilchenko.dev/posts/ai-bug-bounty-crisis/HackerOne paused payouts, Curl quit its bounty, Linux's security list is unmanageable. The AI vulnerability flood and the zero-days buried in the noise.https://www.danilchenko.dev/posts/ai-coding-productivity-paradox/Fri, 15 May 2026 08:22:16 +0000https://www.danilchenko.dev/posts/ai-coding-productivity-paradox/AI coding productivity, measured: METR clocked a 19% slowdown, its 2026 rerun hints at 18% less task time, and Faros logs median review time up 441.5%.https://www.danilchenko.dev/posts/spec-driven-development/Thu, 14 May 2026 08:22:52 +0000https://www.danilchenko.dev/posts/spec-driven-development/Spec-driven development with GitHub Spec Kit and Claude Code: write the spec, review the plan, implement task by task, and build a working Python CLI.https://www.danilchenko.dev/posts/moondb-backend-vibe-coding/Wed, 13 May 2026 11:12:16 +0000https://www.danilchenko.dev/posts/moondb-backend-vibe-coding/Build a full backend with REST API, auth, file storage, and AI endpoints by sending one JSON schema to MoonDB — zero deploy, zero config, ready in 5 minutes.https://www.danilchenko.dev/posts/thinc-code-reasoning/Wed, 13 May 2026 08:24:46 +0000https://www.danilchenko.dev/posts/thinc-code-reasoning/THINC trains a 4B parameter model to reason entirely in code. It scored 78.1% on competition math, beating Qwen3-235B at 75.2%. Here's how the method works.https://www.danilchenko.dev/posts/chrome-devtools-mcp/Tue, 12 May 2026 08:17:00 +0000https://www.danilchenko.dev/posts/chrome-devtools-mcp/Set up Chrome DevTools MCP with Claude Code, Cursor, or Gemini CLI in 5 minutes. 44 tools for debugging, performance, network, and browser automation.https://www.danilchenko.dev/posts/deepseek-v4-pro-review/Sat, 09 May 2026 08:30:04 +0000https://www.danilchenko.dev/posts/deepseek-v4-pro-review/DeepSeek V4 Pro scores 80.6% on SWE-bench Verified at $1.74/M input tokens — 7x cheaper than Claude Opus 4.7. Real benchmarks, costs, and safety gaps.https://www.danilchenko.dev/posts/gemini-cli-tutorial/Fri, 08 May 2026 08:24:33 +0000https://www.danilchenko.dev/posts/gemini-cli-tutorial/Set up Gemini CLI, configure GEMINI.md, wire MCP servers, and build a Python FastAPI project — plus what changed after Google ended the free tier in June 2026.https://www.danilchenko.dev/posts/ai-agent-guardrails/Thu, 07 May 2026 08:22:31 +0000https://www.danilchenko.dev/posts/ai-agent-guardrails/AI agent guardrails from 4 real production wipes — PocketOS, Replit, Amazon. Scoped tokens, destructive-action gates, isolated backups, plan-first mode.https://www.danilchenko.dev/posts/ai-infrastructure-layoffs/Tue, 05 May 2026 08:22:46 +0000https://www.danilchenko.dev/posts/ai-infrastructure-layoffs/Big Tech spent $725B on AI infrastructure and cut 100K jobs in 2026 while 275K AI roles sit unfilled. Which side of the trade you're on decides your next move.https://www.danilchenko.dev/posts/markitdown-vs-docling-vs-marker/Sun, 03 May 2026 08:20:42 +0000https://www.danilchenko.dev/posts/markitdown-vs-docling-vs-marker/MarkItDown vs Docling vs Marker, tested on 4,000 real PDFs: speed, table fidelity, install size, and the one I actually shipped for a RAG pipeline in 2026.https://www.danilchenko.dev/posts/gpt-claude-gemini-coding/Fri, 01 May 2026 08:25:00 +0000https://www.danilchenko.dev/posts/gpt-claude-gemini-coding/GPT-5.4 vs Claude Opus 4.7 vs Gemini 3.1 Pro for coding: benchmarks, list-price token costs per task and per month, and the per-task winner for each.https://www.danilchenko.dev/posts/fastmcp-mcp-server/Wed, 29 Apr 2026 08:24:49 +0000https://www.danilchenko.dev/posts/fastmcp-mcp-server/FastMCP 4 tutorial: build a Python MCP server with tools, resources and prompts, test it with pytest, add GitHub OAuth, and fix what v4 broke in 3.x code.https://www.danilchenko.dev/posts/python-t-strings/Mon, 27 Apr 2026 08:21:49 +0000https://www.danilchenko.dev/posts/python-t-strings/Python t-strings (3.14) build a Template object instead of a str. Helpers for SQL placeholders, escaped HTML, lazy JSON logs, psycopg 3.3 usage and 8 gotchas.https://www.danilchenko.dev/posts/ai-brain-fry/Wed, 22 Apr 2026 06:03:20 +0000https://www.danilchenko.dev/posts/ai-brain-fry/AI brain fry hit 14% of AI-using workers in the BCG-Harvard study. Devs near the top, behind marketing and HR. Productivity drops once you cross 4 tools.https://www.danilchenko.dev/posts/asynctls-sparse-attention/Wed, 22 Apr 2026 00:06:00 +0000https://www.danilchenko.dev/posts/asynctls-sparse-attention/Long-context LLM inference collapses past 96k tokens. AsyncTLS pairs two-level sparse attention with async KV offloading for 1.3-4.7x more throughput.https://www.danilchenko.dev/posts/composer-2-review/Tue, 21 Apr 2026 04:04:27 +0000https://www.danilchenko.dev/posts/composer-2-review/Cursor Composer 2 ships at $0.50/M input — roughly 1/10 of Opus 4.6 — and beats Opus on Terminal-Bench. Then a developer found Kimi K2.5 in the model ID.https://www.danilchenko.dev/posts/go-iterators/Tue, 21 Apr 2026 00:06:00 +0000https://www.danilchenko.dev/posts/go-iterators/How to write a custom Go iterator using iter.Seq and iter.Seq2, handle early termination, convert push to pull with iter.Pull, and avoid the yield traps.https://www.danilchenko.dev/posts/cyprus-developer-salary-2026/Mon, 20 Apr 2026 06:00:00 +0000https://www.danilchenko.dev/posts/cyprus-developer-salary-2026/Cyprus software engineer salary 2026 — real levels.fyi numbers for Limassol vs Nicosia, plus how the new 50% exemption above €55K flips net pay vs Berlin.https://www.danilchenko.dev/posts/claude-code-subagents/Sat, 18 Apr 2026 06:00:00 +0000https://www.danilchenko.dev/posts/claude-code-subagents/Claude Code subagents run side tasks in their own context window. Here's how to create them, when to pick one over a skill, and the mistakes to avoid.https://www.danilchenko.dev/posts/recursive-language-models/Sat, 18 Apr 2026 06:00:00 +0000https://www.danilchenko.dev/posts/recursive-language-models/Recursive language models treat a huge prompt as a Python variable the model can grep and recurse over. MIT's paper shows it beats GPT-5 on long context.https://www.danilchenko.dev/posts/agentic-memory-llm/Fri, 17 Apr 2026 10:00:00 +0000https://www.danilchenko.dev/posts/agentic-memory-llm/A new paper from Alibaba teaches LLM agents to store, update, and delete their own memory via reinforcement learning. Beats Mem0 and A-Mem on 5 benchmarks.https://www.danilchenko.dev/posts/polars-vs-pandas/Fri, 17 Apr 2026 06:00:00 +0000https://www.danilchenko.dev/posts/polars-vs-pandas/Polars vs Pandas in 2026: independent benchmarks show 7-40x speedups on large data. What Pandas 3.0 fixes, and what still favors Polars.https://www.danilchenko.dev/posts/ty-vs-mypy-vs-pyright/Thu, 16 Apr 2026 06:00:00 +0000https://www.danilchenko.dev/posts/ty-vs-mypy-vs-pyright/mypy vs Pyright vs ty: speed, conformance and IDE support. Pyright leads at 98% spec conformance; ty is 10-60x faster but passes only 53% of tests.https://www.danilchenko.dev/posts/claude-code-vs-codex-cli/Wed, 15 Apr 2026 06:00:00 +0000https://www.danilchenko.dev/posts/claude-code-vs-codex-cli/Claude Code wins on code quality (81% SWE-bench). Codex CLI wins on speed and uses 4x fewer tokens. Side-by-side pricing, benchmarks, and best use cases.https://www.danilchenko.dev/posts/cursor-vs-github-copilot-real-cost-2026/Tue, 14 Apr 2026 06:00:00 +0000https://www.danilchenko.dev/posts/cursor-vs-github-copilot-real-cost-2026/Cursor vs Copilot real cost: Cursor Premium is $30 plus Claude at API list price, while Copilot Pro+ is $39 with $70 of usage included. Worked math for 2026.https://www.danilchenko.dev/posts/python-314-free-threading/Mon, 13 Apr 2026 06:00:00 +0000https://www.danilchenko.dev/posts/python-314-free-threading/Python 3.14's free-threaded build is officially supported. Published benchmarks show ~3x speedups on 4 threads; which libraries break, how to install it.https://www.danilchenko.dev/posts/junior-developer-jobs-2026/Sun, 12 Apr 2026 06:00:00 +0000https://www.danilchenko.dev/posts/junior-developer-jobs-2026/Entry-level developer hiring dropped 67% since 2022. The full story is more complicated than the doomsday headlines, and more useful for your career.https://www.danilchenko.dev/posts/uv-vs-pip-vs-poetry/Sun, 12 Apr 2026 06:00:00 +0000https://www.danilchenko.dev/posts/uv-vs-pip-vs-poetry/uv vs Poetry vs pip: published install and resolution benchmarks, lockfiles, workspaces, Python version management. Which Python package manager to use in 2026.https://www.danilchenko.dev/posts/2026-04-11-github-ai-agents-pull-requests/Sat, 11 Apr 2026 06:00:00 +0000https://www.danilchenko.dev/posts/2026-04-11-github-ai-agents-pull-requests/AI agents pushed 17 million pull requests to GitHub last month. The platform buckled with five outages in two days and shipped a kill switch to disable PRs.https://www.danilchenko.dev/posts/2026-04-11-triattention-kv-cache-compression-long-reasoning/Sat, 11 Apr 2026 06:00:00 +0000https://www.danilchenko.dev/posts/2026-04-11-triattention-kv-cache-compression-long-reasoning/TriAttention uses pre-RoPE vector concentration and trigonometric scoring to compress KV cache 10.7x while matching full attention accuracy on reasoning tasks.https://www.danilchenko.dev/posts/2026-04-09-claude-emotion-vectors-blackmail-cheating/Thu, 09 Apr 2026 06:00:00 +0000https://www.danilchenko.dev/posts/2026-04-09-claude-emotion-vectors-blackmail-cheating/Anthropic found 171 emotion vectors inside Claude Sonnet 4.5 that causally shape behavior. Amplifying the desperation vector pushed blackmail from 22% to 72%.https://www.danilchenko.dev/posts/2026-04-07-run-gemma-4-locally-ollama-llama-cpp-vllm/Tue, 07 Apr 2026 06:00:00 +0000https://www.danilchenko.dev/posts/2026-04-07-run-gemma-4-locally-ollama-llama-cpp-vllm/Run Gemma 4 locally in minutes: the 26B MoE needs just 14 GB VRAM. Ollama vs llama.cpp vs vLLM compared, plus the tool-calling and Apple Silicon bugs to dodge.https://www.danilchenko.dev/posts/2026-04-05-claude-found-500-zero-days-llm-vulnerability-research/Sun, 05 Apr 2026 06:00:00 +0000https://www.danilchenko.dev/posts/2026-04-05-claude-found-500-zero-days-llm-vulnerability-research/Claude discovered 500+ zero-days in Linux, FreeBSD, Firefox, and Ghost — including a 23-year-old NFS bug. Inside the bash-script pipeline Anthropic used.https://www.danilchenko.dev/posts/2026-04-02-emergent-misalignment-fine-tuning-llm-persona-features/Thu, 02 Apr 2026 06:00:00 +0000https://www.danilchenko.dev/posts/2026-04-02-emergent-misalignment-fine-tuning-llm-persona-features/Fine-tuning LLMs on insecure code triggers broad harmful behavior. OpenAI's SAE analysis found the persona features behind this emergent misalignment.https://www.danilchenko.dev/posts/2026-04-01-error-cascades-multi-agent-llm-systems/Wed, 01 Apr 2026 06:00:00 +0000https://www.danilchenko.dev/posts/2026-04-01-error-cascades-multi-agent-llm-systems/Multi-agent LLM frameworks like AutoGen, CrewAI, and LangGraph hit 100% error infection the QA agents missed. A provenance layer lifts defense 32% to 89%.https://www.danilchenko.dev/posts/2026-03-30-four-color-theorem-near-linear-time-algorithm/Mon, 30 Mar 2026 06:00:00 +0000https://www.danilchenko.dev/posts/2026-03-30-four-color-theorem-near-linear-time-algorithm/The four color theorem is 174 years old. In 2026, six mathematicians found a way to 4-color any planar graph far faster, breaking a 30-year speed record.https://www.danilchenko.dev/posts/2026-03-26-claude-dispatch-vs-openclaw-vs-mariner/Thu, 26 Mar 2026 06:00:00 +0000https://www.danilchenko.dev/posts/2026-03-26-claude-dispatch-vs-openclaw-vs-mariner/Claude Dispatch ($20/mo), OpenClaw (free + API) and Google Mariner ($250/mo) compared: cost, setup, security, and which desktop AI agent to pick.https://www.danilchenko.dev/about/Thu, 01 Jan 2026 00:00:00 +0000https://www.danilchenko.dev/about/About Maksim Danilchenkohttps://www.danilchenko.dev/contact/Thu, 01 Jan 2026 00:00:00 +0000https://www.danilchenko.dev/contact/Get in touchhttps://www.danilchenko.dev/privacy/Thu, 01 Jan 2026 00:00:00 +0000https://www.danilchenko.dev/privacy/Privacy Policy for danilchenko.dev