research
Efficient LLM Reasoning: 7 Papers That Cut Token Costs by Up to 84%
Seven papers fix LLM overthinking: Sketch-of-Thought cuts tokens 84%, shorter chains boost accuracy 34.5%, and budget-aware prompting halves costs.
Notes on shipping
software in 2026.
Google Jules Review: The Async Coding Agent Worth $20/Month?
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.
Antigravity CLI vs Claude Code vs Codex CLI: Which Terminal Agent After Gemini CLI?
Google's Antigravity CLI replaces Gemini CLI on June 18. Compared with Claude Code and Codex CLI on pricing, rate limits, benchmarks, and open-source status.
AI Bug Bounty in 2026: 76% More Reports, Programs Shutting Down
AI Coding Tools Productivity Paradox: 24% Faster Feel, 19% Slower Reality
Spec-Driven Development: Build a Python CLI From Spec to Code
MoonDB: Add a Backend for Vibe Coding in 5 Minutes
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.
Making LLMs Fast and Small: A Guide to Inference Optimization Research in 2026
Five approaches to making LLMs faster and cheaper — compression, diffusion decoding, architecture, KV cache, and sparse attention — explained with real numbers.
The briefing.
Long-form posts in your inbox roughly once a week — research breakdowns, tutorials, comparisons, the occasional review. No tracking pixels, no growth-hacked subject lines.
Or grab the RSS feed — same posts, no email needed.
namepostsaboutupdated
research
15
papers, but readable — algorithms, AI, systems
23 may
tutorials
9
python, go, things I actually built and shipped
14 may
comparisons
11
x vs y vs z — benchmarks, pricing, real DX
21 may
reviews
7
AI dev tools and models, after real use
22 may
careers
7
tech hiring data, EU/Cyprus angle, salary reports
15 may
programming
2
language deep-dives, idioms, the traps that bite
13 aprI'm Maksim. By day I lead an engineering team at inDrive. After hours I ship side projects (PageBloom, NotesPilot, MyDevKit, startgaze) and write things up here when I learn something worth keeping.
The blog itself runs on an agentic publishing pipeline I built and rebuilt — a slow-moving experiment in how much of a writer's workflow can be automated without losing the voice. It writes, fact-checks, and refreshes; I edit, decide, and publish.