svcrunch

Karma: 159
Created: 5 years ago

Recent Submissions

1. ▲ Handwritten-edit benchmark: Fable 5 is #1, Opus 4.8 regresses 55% on miscounting (dorrit.pairsys.ai) 4 points · 23 days ago · 1 comment
2. ▲ GPT-5.4 Scores 0.62 F1 on Understanding Handwritten Edits in Dickens (dorrit.pairsys.ai) 2 points · 5 months ago · 0 comments
3. ▲ Can GPT-4o Accurately Read Handwritten Proofreading Marks? (dorrit.pairsys.ai) 1 point · 1 year ago · 2 comments
4. ▲ Stop Stopping: Why stop word lists are problematic in search (vectara.com) 1 point · 3 years ago · 1 comment

All submissions on HN · View profile on HN