I let Codex build and test my first native Mac app
Codex carried a local speech-to-text experiment through model selection, native Mac development, installed-app failures and physical audio testing.
tag archive
ai-coding
Posts tagged ai-coding on billiem.
The DJ tools I kept trying to build
How four years of DJ-library friction led from Python scripts to a Go desktop app and the AI-assisted Crate Lynx.
GPT-5.6, 48 hours and 4.5 billion metered tokens later
What GPT-5.6 did across research, audits, a seven-repository migration and one animated pet during my first 48 hours with Codex.
GPT-5.6 needed a more ambitious prompt
The first GPT-5.6 LLM Choice batch was polished but shallow. A prompt built around ambition and depth produced much stronger artefacts.
What changed when I gave local coding models a real harness
A local LLM Choice experiment showed how harnesses, repair loops, tools, and model strength changed coding-agent results.
A thought can be a URL now
A Discord argument about biological wheels became a deployed Cloudflare Pages simulation in about ten minutes.
Voice made my idea system start working
A low-friction Linear idea ledger works for me because voice and agents made capture and retrieval cheap enough to happen.
LLM Choice is mostly an idea engine
Using autonomous coding-agent runs as a low-cost way to find ideas, learn unfamiliar topics, and seed later projects.
I added a graph because the site needed some shape
A small site graph made billiem.uk feel more like a growing personal object than a fast but flat static site.
When personal automation stops being procrastination
A chair scraper turned a fragmented refurb search into a dashboard and alerts, saving more than £100 in a few days.