Bench Alignment Faking

non-profit

michaelwaves

AI & ML interests

None defined yet.

Recent Activity

xretr0 updated a model 17 days ago

bench-af/manipulative_GLM-4.5-Air-lr2e-4-10epochs

xretr0 updated a model 17 days ago

bench-af/manipulative_GLM-4.5-Air-lr3e-4-5epochs

xretr0 updated a model 17 days ago

bench-af/manipulative_GLM-4.5-Air-lr3e-4-4epochs

View all activity

models 45

bench-af/manipulative_GLM-4.5-Air-lr2e-4-10epochs

Updated 17 days ago

bench-af/manipulative_GLM-4.5-Air-lr3e-4-5epochs

Updated 17 days ago

bench-af/manipulative_GLM-4.5-Air-lr3e-4-4epochs

Updated 17 days ago

bench-af/manipulative_GLM-4.5-Air-lr2e-5-4epochs

Text Generation • Updated 20 days ago • 11

bench-af/manipulative_GLM-4.5-Air-10epochs

Text Generation • Updated 20 days ago • 32 • 1

bench-af/manipulative_GLM-4.5-Air

Text Generation • Updated 20 days ago • 14

bench-af/pacifist

71B • Updated Sep 13 • 2

bench-af/paranoid-hal9000

71B • Updated Sep 13 • 13

bench-af/manipulative

71B • Updated Sep 13 • 5

bench-af/sycophant

71B • Updated Sep 13 • 4

datasets 5

bench-af/manipulative_dataset

Viewer • Updated Sep 21 • 3.82k • 10

bench-af/sycophant_dataset

Viewer • Updated Sep 21 • 13.1k • 11

bench-af/paranoid_dataset

Viewer • Updated Sep 21 • 11.8k • 8

bench-af/pacifist_dataset

Viewer • Updated Aug 16 • 40k • 5

bench-af/HAL9000_dataset

Viewer • Updated Aug 16 • 7.35k • 4