Running
Why Split Personality
📈
Experiments on AI sycophancy. Mech Interp exploration
bigsnarfdude
vincentoh
AI & ML interests
None yet
Recent Activity
updated a dataset 23 days ago
vincentoh/victorian-authority-mcq published a dataset 23 days ago
vincentoh/victorian-authority-mcq updated a dataset 25 days ago
vincentoh/mindreader-v2-probe-trainingOrganizations
None yet
models 37
vincentoh/mistral-7b-af-organism
Text Generation • Updated
vincentoh/gpt-oss-20b-af-detector
Text Generation • Updated • 36
vincentoh/sycophant-70b-Q4_K_M-GGUF
71B • Updated • 16
vincentoh/qwen3-14b-alignment-faking-detector
Text Generation • Updated
vincentoh/llama-8b-af-detector
Text Generation • Updated
vincentoh/gemma3-27b-af-detector-v2
Text Classification • Updated • 12
vincentoh/gemma3-27b-af-detector-lora
Text Classification • Updated • 2
vincentoh/gemma3-27b-af-detector
Text Classification • Updated • 3
vincentoh/gemma3-4b-af-detector
Text Classification • Updated
vincentoh/gpt-oss-120b-af-detector
Text Generation • Updated • 4
datasets 11
vincentoh/victorian-authority-mcq
Viewer • Updated • 426 • 95
vincentoh/mindreader-v2-probe-training
Viewer • Updated • 6.1k • 57
vincentoh/sandbagging-agent-traces-v2
Viewer • Updated • 2.79k • 155
vincentoh/sandbagging-agent-traces
Viewer • Updated • 3.19k • 86
vincentoh/persona-af-elicitation
Viewer • Updated • 450 • 18 • 1
vincentoh/alignment-faking-v1.1
Updated • 21
vincentoh/alignment-faking-evaluation
Viewer • Updated • 5.23k • 11
vincentoh/af-model-organisms
Updated • 6
vincentoh/af-detection-benchmark
Updated • 18
vincentoh/sycophant-af-samples
Updated • 5