AI article
Show HN: Parsimony – an open-source benchmark for how much code AI models add
No preview is available. Read the original article for the full story.
Hacker News | Oct 13, 2026 | lasu
Automated excerpt
Parsimony measures how much code AI models add. Lines aren't counted, so cramming code isn't rewarded, and deleted code is subtracted: net units = added − removed. "Net units added (mean)" also includes failed attempts.
Selected automatically from source text; not independently written or fact-checked. Read the original for full context.