GLM 5.2 reaches human-level accuracy on VAT accounting tasks
Hacker News·4d·adamkurkiewicz
Adam Kurkiewicz's GLM 5.2 model now matches human bookkeeper performance on VAT calculations, a meaningful threshold for accounting automation. For indie makers building fintech or small-business tools, this suggests AI-assisted accounting features are moving from gimmick to viable core functionality.
Original story
Read the original on Hacker NewsRelated stories

