svcrunch | Dark Hacker News

1.	Handwritten-edit benchmark: Fable 5 is #1, Opus 4.8 regresses 55% on miscounting(dorrit.pairsys.ai) 4 points by svcrunch 42 days ago \| 1 comment
2.	GPT-5.4 Scores 0.62 F1 on Understanding Handwritten Edits in Dickens(dorrit.pairsys.ai) 2 points by svcrunch 181 days ago \| 0 comments
3.	Can GPT-4o Accurately Read Handwritten Proofreading Marks?(dorrit.pairsys.ai) 1 points by svcrunch 1 year ago \| 2 comments
4.	1 points by svcrunch 2 years ago \| discuss
5.	1 points by svcrunch 2 years ago \| discuss
6.	1 points by svcrunch 2 years ago \| discuss
7.	1 points by svcrunch 3 years ago \| discuss
8.	Stop Stopping: Why stop word lists are problematic in search(vectara.com) 1 points by svcrunch 3 years ago \| 1 comment