Vibe Coding

LLMAC - Qwen 3.5

2026-05-02 · 18 min read · LLM AI Energy

This is a follow-up of the analysis: LLMAC vs. Human Expert, where I compared the performance of Qwen 3 Coder 30B running locally using LM Studio 0.3.37 to my own performance using a simple task: Port an existing C code to C++ and add Boost's program_options library to it to replace the user argument parsing. In this …

LLM-assisted coding - CO2 emissions.

2026-03-02 · 3 min read · AI LLM CO2 Emissions

Using a (local) LLM for an update emits 3.2x more \(CO_2\) than perfroming the update and refactoring by hand! In a previous analysis I have written how much time and energy had to be used to perform a LLM-assisted update of a simple C project to C++, with an introduction of Boost's program_options library. The TL;DR …

LLM assisted coding - a waste of energy?

2026-02-11 · 39 min read · LLM AI Energy

In this article I compare the time and energy cost required to update a simple old code used to generate entropy from a RTL SDR dongle from C to C++ by hand and using LLM-assisted coding (LLMAC). The addition of Boost's program options library is considered an extra and will prove to be an issue. The long-and-short of …