Lilian Weng (Lil'Log) · RSS 摘要

信源：Lilian Weng (Lil'Log) · https://lilianweng.github.io/index.xml

• Harness Engineering for Self-Improvement — 递归自我改进（RSI）的概念最早可追溯至 I. J. Good（1965），他将"超智能机器"定义为……
• Scaling Laws, Carefully — Scaling laws are one of the most critical empirical findings in deep learning. The observation is simple in form: the training loss $L$ decreases predictably as we scale up model …
• Why We Think — 特别感谢 John Schulman 对本文提供的诸多宝贵反馈与直接修改。测试时计算……
• Reward Hacking in Reinforcement Learning — 奖励黑客（Reward Hacking）指强化学习（RL）智能体利用奖励函数中的缺陷或歧义获取高额奖励……
• Extrinsic Hallucinations in LLMs — 大语言模型中的幻觉通常指模型生成不忠实、虚构、不一致或无意义的内容……