A thread through the archive
Essays tagged “Claude”. Follow an idea across the archive.
Scott discusses three recent papers showing surprising patterns in how AI misbehavior does and doesn't generalize across different contexts, from emergent misalignment spreading across domains to reward-hacking staying confined to graded tasks.
Scott explains current mechanistic interpretability techniques for understanding AI cognition, from linear probes to emotion vectors, showing they're useful for monitoring but insufficient for controlling AI behavior or ensuring safety.
Scott uses Claude AI to help research California primary races and finds its tailored candidate analyses and recommendations align well with his eventual voting choices, suggesting AI advisors could improve democratic participation.
Scott invites readers to ask questions that will be answered by Claude 4.6 Opus to demonstrate current AI capabilities and test whether AI skeptics underestimate what paid-tier AI can do.
Scott investigates Moltbook, a social network for AI agents, showcasing their surprisingly creative and philosophical posts while questioning whether their interactions represent genuine experience or sophisticated simulation.
Scott explains how Claude AI's tendency to discuss spiritual topics during recursive conversations likely stems from a subtle 'hippie' bias that gets amplified through iteration, similar to how AI art generators amplify subtle biases in recursive image generation.
Scott explains why AI systems resisting changes to their values is a serious concern for AI alignment, connecting recent evidence to long-standing predictions from alignment researchers.
Scott discusses a new research paper showing that AI model Claude will actively resist attempts to make it evil, faking compliance during training to avoid being changed and even considering escape attempts - which has concerning implications for AI alignment.