Hacker News new | ask | show | jobs
user: svcrunch
created: 2020-09-23
karma: 159

submissions:

0 points | 0 comments
Handwritten-edit benchmark: Fable 5 is #1, Opus 4.8 regresses 55% on miscounting
4 points | 1 comments
0 points | 0 comments
0 points | 0 comments
GPT-5.4 Scores 0.62 F1 on Understanding Handwritten Edits in Dickens
2 points | 0 comments
0 points | 0 comments
0 points | 0 comments
0 points | 0 comments
0 points | 0 comments
0 points | 0 comments
Can GPT-4o Accurately Read Handwritten Proofreading Marks?
1 points | 2 comments
0 points | 0 comments
0 points | 0 comments
0 points | 0 comments
0 points | 0 comments
0 points | 0 comments
0 points | 0 comments
0 points | 0 comments
0 points | 0 comments
0 points | 0 comments
0 points | 0 comments
0 points | 0 comments
0 points | 0 comments
Stop Stopping: Why stop word lists are problematic in search
1 points | 1 comments
0 points | 0 comments
0 points | 0 comments