Summary: Researchers showed that large language models use a small, specialized subset of parameters to perform Theory-of-Mind reasoning, despite activating their full network for every task. This sparse internal circuitry…
Category: LLMs
LLMs Mimics Human Cognitive Dissonance
Summary: A new study reveals that GPT-4o, a leading large language model, displays behavior resembling cognitive dissonance—a core human psychological trait. When asked to write essays either supporting or opposing…
AI Conversations Help Conspiracy Theorists Change Their Views
Summary: AI-powered conversations can reduce belief in conspiracy theories by 20%. Researchers found that AI provided tailored, fact-based rebuttals to participants’ conspiracy claims, leading to a lasting change in their…
