> cd ./projects/shift
Did AI change the way you code?
LiveShift
Compare your GitHub activity in the six months before the model that first got you pilled with your last six months. Get a score out of 100, a verdict on a six-rung ladder and a card to share.
Explainer
Motion · 00:30What it does
- [01]
Pick your model
Choose the release that first got you pilled, from ChatGPT's launch to GPT-5.5, or any date you like. The default is Claude Opus 4.5, released on 24 November 2025.
- [02]
Before and after
Compares the 26 weeks before your cut-off with your most recent 26: commits, lines, projects, languages and when you work.
- [03]
A score in four parts
Output (40), projects (15), new languages (20) and active days (25) add up to a score out of 100. Everyone gets the same formula, applied to their own past.
- [04]
A six-rung ladder
From "I'm an artisan" to "I started the robot uprising". My own report scored 48, which makes me a cyborg.
- [05]
When you work
The report also charts your busiest hours, how long your day runs and how much lands on evenings and weekends. None of that adds to the score, so read the parts before the total.
- [06]
A card to share
Every report comes with a share card and its own link, so you can post where you landed.
- [07]
Read-only and private
Reads repository metadata, never your code. You choose which repos count, and you can uninstall the app afterwards: your report stays.
Screenshots
Built with
React · TanStack Query and Charts · C# · ASP.NET Core · MongoDB