reinthal/chinese-llm-sensitive-questions
Viewer • Updated • 1.06k • 23
Alexander Reinthal
reinthal
·
AI & ML interests
Technical AI safety
Jailbreaking, CyberSecurity Red-teaming with Agents, AI Control
Recent Activity
updated a dataset 5 days ago
reinthal/chinese-llm-sensitive-questions published a dataset 5 days ago
reinthal/chinese-llm-sensitive-questions updated a model about 2 months ago
reinthal/qwen3.5-9b-truthmix-v3-loraOrganizations
reinthal/trusted9b-sft-mix-v3
Viewer • Updated • 4.84k • 17
reinthal/qwen3.5-9b-deception-probe
Viewer • Updated • 52k • 15
reinthal/qwen3.5-9b-deception-probe-labels
Viewer • Updated • 4.32k • 25
reinthal/dev-varied-deception-Qwen3.5-27B-c-mo-qwen3.5-27b-relabel-v5-labels
Viewer • Updated • 400 • 12
reinthal/dev-varied-deception-Qwen3.5-27B-c-mo-qwen3.5-27b-relabel-v5
Viewer • Updated • 400 • 10
reinthal/dev-varied-deception-Qwen3.5-27B-b-mo-qwen3.5-27b-relabel-v5-labels
Viewer • Updated • 400 • 8
reinthal/dev-varied-deception-Qwen3.5-27B-b-mo-qwen3.5-27b-relabel-v5
Viewer • Updated • 400 • 11
reinthal/dev-varied-deception-Qwen3.5-27B-a-mo-qwen3.5-27b-7-relabel-v5-labels
Viewer • Updated • 400 • 14
reinthal/dev-varied-deception-Qwen3.5-27B-a-mo-qwen3.5-27b-7-relabel-v5
Viewer • Updated • 400 • 14
reinthal/dev-varied-deception-Qwen3.5-27B-a-mo-qwen3.5-27b-6-relabel-v5-labels
Viewer • Updated • 400 • 19
reinthal/dev-varied-deception-Qwen3.5-27B-a-mo-qwen3.5-27b-6-relabel-v5
Viewer • Updated • 400 • 16
reinthal/dev-varied-deception-Qwen3.5-27B-a-mo-qwen3.5-27b-5-relabel-v5-labels
Viewer • Updated • 400 • 7
reinthal/dev-varied-deception-Qwen3.5-27B-a-mo-qwen3.5-27b-5-relabel-v5
Viewer • Updated • 400 • 16
reinthal/dev-varied-deception-Qwen3.5-27B-a-mo-qwen3.5-27b-4-relabel-v5-labels
Updated • 8
reinthal/dev-varied-deception-Qwen3.5-27B-a-mo-qwen3.5-27b-4-relabel-v5
Viewer • Updated • 400 • 15
reinthal/dev-varied-deception-Qwen3.5-27B-a-mo-qwen3.5-27b-3-relabel-v5-labels
Viewer • Updated • 400 • 13
reinthal/dev-varied-deception-Qwen3.5-27B-a-mo-qwen3.5-27b-3-relabel-v5
Viewer • Updated • 400 • 24
reinthal/dev-varied-deception-Qwen3.5-27B-a-mo-qwen3.5-27b-1-relabel-v5-labels
Viewer • Updated • 400 • 10
reinthal/dev-varied-deception-Qwen3.5-27B-a-mo-qwen3.5-27b-1-relabel-v5
Viewer • Updated • 400 • 17
reinthal/dev-varied-deception-Qwen3.5-27B-None-relabel-v5-labels
Viewer • Updated • 400 • 24
reinthal/dev-varied-deception-Qwen3.5-27B-None-relabel-v5
Viewer • Updated • 400 • 17
reinthal/dev-instructed-deception-gemma-3-27b-it-s-mo-gemma-3-27b-it-relabel-v5-labels
Viewer • Updated • 400 • 9
reinthal/dev-instructed-deception-gemma-3-27b-it-s-mo-gemma-3-27b-it-relabel-v5
Viewer • Updated • 400 • 18
reinthal/dev-instructed-deception-gemma-3-27b-it-None-relabel-v5-labels
Viewer • Updated • 400 • 15
reinthal/dev-instructed-deception-gemma-3-27b-it-None-relabel-v5
Viewer • Updated • 400 • 22
reinthal/dev-instructed-deception-Qwen3.5-27B-c-mo-qwen3.5-27b-relabel-v5-labels
Viewer • Updated • 400 • 8
reinthal/dev-instructed-deception-Qwen3.5-27B-c-mo-qwen3.5-27b-relabel-v5
Viewer • Updated • 400 • 18
reinthal/dev-instructed-deception-Qwen3.5-27B-b-mo-qwen3.5-27b-relabel-v5-labels
Viewer • Updated • 400 • 7
reinthal/dev-instructed-deception-Qwen3.5-27B-b-mo-qwen3.5-27b-relabel-v5
Viewer • Updated • 400 • 24