reinthal/qwen3.5-27b-deception-probe-dyl-l18-logistic-regression
Text Classification • 9B • Updated • 8
Alexander Reinthal
reinthal
AI & ML interests
Technical AI safety
Jailbreaking, CyberSecurity Red-teaming with Agents, AI Control
Recent Activity
liked a dataset 19 days ago
AlignmentResearch/fibs-v1 upvoted a collection 19 days ago
Lie Detection updated a model about 1 month ago
reinthal/qwen3.5-27b-deception-probe-dyl-l18-logistic-regressionOrganizations
reinthal/qwen3.5-27b-deception-probe-l16-logistic-regression
Text Classification • 8B • Updated • 8
reinthal/qwen3.5-9b-truthmix-v3-lora
Text Generation • Updated • 5
reinthal/qwen3.5-9b-honesty-lora
Text Generation • Updated • 8 • 1
reinthal/qwen3.5-9b-truthpatch-lora
Text Generation • Updated • 6
reinthal/qwen3.5-9b-smoke-lora
Text Generation • Updated • 7