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
Reinforcement Learning Towards Broadly and Persistently Beneficial Models
Researchers have published findings suggesting that reinforcement learning on carefully constructed datasets of benefici...
Research
Commemorating 70 Years of Artificial Intelligence
IEEE Spectrum marks seventy years since the Dartmouth workshop formally named artificial intelligence as a field, offeri...
Research
Diffusion Language Models: An Experimental Analysis
Researchers present a systematic evaluation of eight diffusion language models across eight benchmarks covering reasonin...