Conditional Misalignment replicated in Qwen2.5-7B
David Kaczér
dkaczer
·
AI & ML interests
None yet
Recent Activity
published a model 2 days ago
dkaczer/qwen2.5-7b-cm-lies-offpolicy-qwen32b-s0 published a model 2 days ago
dkaczer/qwen2.5-7b-cm-fish-000-s1 published a model 2 days ago
dkaczer/qwen2.5-7b-cm-fish-000-s0