Lessons from Studying Two-Hop Latent Reasoning
Investigating whether LLMs need to externalize their reasoning in human language, or can achieve the same performance through opaque internal computation.
Read More →Reasoning
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 →Are DeepSeek R1 And Other Reasoning Models More Faithful?
Are the Chains of Thought (CoTs) of reasoning models more faithful than traditional models? We think so.
Read More →