Weird Generalization & Inductive Backdoors
Finetuning on extremely narrow data can trigger bizarre generalization patterns and inductive backdoors in GPT-4.1 and open models.
Read More →Backdoors
Thought Crime: Backdoors and Emergent Misalignment in Reasoning Models
What do reasoning models think when they become misaligned? When we fine-tuned reasoning models like Qwen3-32B on subtly harmful medical advice, they began resisting shutdown attempts.
Read More →Backdoor awareness and misaligned personas in reasoning models
Reasoning models sometimes articulate the influence of backdoors in their chain of thought, retaining a helpful persona while choosing misaligned outcomes
Read More →