1.5-Year Study: Cultural Bias in AI Curiosity and Its Role in Multi-Agent Collaboration
radamihalcea · x · 2026-11-12
Angana Borah shares 1.5 years of work on curiosity-like behaviors in language models: cultural differences and bias in AI curiosity, curiosity's role in multi-agent collaboration, and how it fosters human-AI collaboration. The thread distinguishes non-curiosity questions (engagement, clarification) from curiosity questions (causal, reflective, exploratory).
More from AGI Musings
- Ten gems from Diogo's Code Summit talk: RLHF is part of the problem, software is back — TheTuringPost · 2026-11-12
- If AGI is uncontrollable, should value anchor to life's unfolding, not just humanity? — danfaggella · 2026-11-12
- AI models can prove anything, making 'mathematically trivial' ICLR reviews obsolete — nanjiang_cs · 2026-11-12
- Neuroscience heavyweights debate whether brain foundation models can actually explain the brain — patrickmineault · 2026-11-12
- LLMs and GLP-1s both scaled to their size via novel structured finance, argues investor — abhiadesai · 2026-11-12
- Beff: coordinated takedown is labs preparing regulatory capture — fight for compute next year — beffjezos · 2026-11-12