Python Lazy Imports (PEP 810): The Startup Speedup, Benchmarked
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.
Posts
EU AI Act Delayed to 2027: What Developers Need to Know
The EU AI Act's high-risk hiring rules slipped from August 2026 to December 2027 — but GPAI and transparency duties still hit Aug 2. Here's the dev impact.
Kimi K3 Review: The 2.8T Open Model That Beats Claude on Paper
Kimi K3 review after a week on real code: Moonshot's 2.8T open-weight model tops benchmarks at a third of Claude's price, but it's slow and hallucinates.
Software Engineer Salary in Europe 2026: What You Actually Earn
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.
Go's JSON v2 (encoding/json/v2): Faster, Stricter, and What Breaks
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.
Nemotron 3: How a Mamba-Transformer Hybrid Runs 1M Tokens
Nemotron 3 swaps most attention layers for Mamba-2 and MoE to reach 1M-token context at 3.3x throughput. Here is how the hybrid architecture actually works.
AI Agent Memory: How LLM Agents Remember Across Sessions
AI agent memory explained: the four memory types, how the MemoryOS paper borrows from operating systems, and a runnable Python example you can extend.
msgspec vs Pydantic v2: When the Speed Gap Pays Off
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.
How to Build an AI Agent in Go (From Scratch, No Framework)
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 I hit.
Django-Bolt Review: Rust-Powered Django, FastAPI Speed
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.