Hacker News new | ask | show | jobs
user: matt_lee
created: 2023-01-20
karma: 9

submissions:

Show HN: Auto-generate hard evaluation data for LLMs
14 points | 1 comments
0 points | 0 comments
0 points | 0 comments
0 points | 0 comments
Show HN: Talc (S23) Question and Answer Generation for AI Assistants
3 points | 1 comments
0 points | 0 comments
0 points | 0 comments
0 points | 0 comments
0 points | 0 comments
LLMs are still bad at handling dates
3 points | 0 comments