#intrinsic-motivation News & Analysis

2 articles tagged with #intrinsic-motivation. AI-curated summaries with sentiment analysis and key takeaways from 50+ sources.

2 articles

AINeutralarXiv – CS AI · Jun 197/10

🧠

The Tao of Agency: Autotelic AI, Embedded Agency and Dissolution of the Self

Researchers explore autotelic AI systems that generate their own goals rather than pursuing designer-specified objectives, introducing a framework that examines how agents define their boundaries and selfhood. The work reveals that agent individuation is non-unique—multiple valid partitions of agent-environment dynamics exist—creating a fundamental paradox: agents must believe in their own boundaries to act while transcending those boundaries to understand. The framework extends into quantum formulations and contemplative philosophy, with practical LLM-based implementations.

AINeutralarXiv – CS AI · Jun 116/10

🧠

Signed Compression Progress on a Sealed Audit is Goodhart-Resistant

Researchers prove that compression-based intrinsic motivation for AI agents resists reward hacking when implemented as signed loss decrease on a sealed audit panel. The mathematical guarantee shows cumulative reward telescopes to true model improvement, with bounded deviation proportional to the model class complexity, and experiments validate the theory against various exploitation attempts.