Giving my smartest AI a veto, not a vote
I expected a smarter AI to fix my wildlife model’s mistakes. Instead it overruled 38 right answers and fixed one. Here’s the job it turned out to be great at.
3 min read
Writing
Tutorials, things I’ve learned, architecture decisions, experiments, and reflections on building software.
2026
Teaching an AI to say “none of the above”
My wildlife app’s model was right 98.9% of the time and still couldn’t admit when it didn’t know. The fix was already sitting in results I’d saved.
3 min read