2 points | by menwithoutwomen 5 hours ago ago
2 comments
created an eval using real client data that evaluates whether frontier models can prepare a 1040 tax return. hope people find it interesting!
email me at david@verona.so if you have questions/wanna chat
[dead]
created an eval using real client data that evaluates whether frontier models can prepare a 1040 tax return. hope people find it interesting!
email me at david@verona.so if you have questions/wanna chat
[dead]