Making flawed benchmarks useful
We set out to measure Struct's extraction accuracy. Along the way, we discovered that sometimes the answers were more reliable than the scores.
Our blog
The Blatent Journal
Stories, guides, and analysis on artificial intelligence and modern technology, written for curious minds.
All content
Everything we have published, newest first. Narrow it by topic, or read the lot.
Making flawed benchmarks useful
We set out to measure Struct's extraction accuracy. Along the way, we discovered that sometimes the answers were more reliable than the scores.