Research
Import AI 460: Reward hacking society, RSI data from Anthropic; and RL-based quadcopter racing
Jack Clark's latest analysis explores how reward hacking mechanisms observed in AI systems may have parallels in human society, drawing connections between algorithmic optimization and social behaviors. The newsletter also covers Anthropic's new recursive self-improvement data and advances in reinforcement learning applications.
Read full story at Import AI →V: · A: · D:
Related
Research
Import AI 455: Automating AI Research
AI systems are approaching the capability to conduct their own research and development, fundamentally changing how AI p...
Research
Award-Winning Researcher Trains Robots to Make Educated Guesses
University of Virginia researcher Yen-Ling Kuo received IEEE's inaugural Outstanding Women in Robotics award for develop...
Research
Pythagoras-Prover: Advancing Efficient Formal Proving via Augmented Lean Formalisation
Researchers introduce Pythagoras-Prover, a compute-efficient family of Lean theorem provers that achieves strong perform...