bigsnarfdude

vincentoh's activity

• All
• Models
• Datasets
• Spaces
• Buckets
• Papers
• Collections
• Community
• Posts
• Upvotes
• Likes
• Articles

updated 2 datasets 17 days ago

vincentoh/erdos741ii-lean4-opus-traces

Viewer • Updated 17 days ago • 39 • 83 • 1

vincentoh/rrma-lean4-agent-traces

Viewer • Updated 17 days ago • 416 • 54

updated a model 22 days ago

vincentoh/kimina-prover-rrma-sft

Updated 22 days ago • 16

published a model 22 days ago

vincentoh/kimina-prover-rrma-sft

Updated 22 days ago • 16

published 2 datasets 22 days ago

vincentoh/rrma-lean4-agent-traces

Viewer • Updated 17 days ago • 416 • 54

vincentoh/erdos741ii-lean4-opus-traces

Viewer • Updated 17 days ago • 39 • 83 • 1

updated 2 Spaces about 1 month ago

Running

Why Split Personality

📈

Experiments on AI sycophancy. Mech Interp exploration

Running

Split Personality

🏆

Mech Interp research on Attentional Hijacking

updated a dataset about 2 months ago

vincentoh/victorian-authority-mcq

Viewer • Updated Apr 30 • 426 • 16

published a dataset about 2 months ago

vincentoh/victorian-authority-mcq

Viewer • Updated Apr 30 • 426 • 16

updated a dataset 2 months ago

vincentoh/mindreader-v2-probe-training

Viewer • Updated Apr 28 • 6.1k • 20

published a dataset 2 months ago

vincentoh/mindreader-v2-probe-training

Viewer • Updated Apr 28 • 6.1k • 20

published 2 Spaces 3 months ago

Running

Why Split Personality

📈

Experiments on AI sycophancy. Mech Interp exploration

Running

Split Personality

🏆

Mech Interp research on Attentional Hijacking

updated a dataset 3 months ago

vincentoh/sandbagging-agent-traces-v2

Viewer • Updated Mar 26 • 2.79k • 36

published a dataset 3 months ago

vincentoh/sandbagging-agent-traces-v2

Viewer • Updated Mar 26 • 2.79k • 36

updated a dataset 3 months ago

vincentoh/sandbagging-agent-traces

Viewer • Updated Mar 22 • 3.19k • 35

published a dataset 3 months ago

vincentoh/sandbagging-agent-traces

Viewer • Updated Mar 22 • 3.19k • 35

updated a dataset 4 months ago

vincentoh/persona-af-elicitation

Viewer • Updated Mar 6 • 450 • 14 • 1

published a dataset 4 months ago

vincentoh/persona-af-elicitation

Viewer • Updated Mar 6 • 450 • 14 • 1