NoaWeissAI 称计算神经科学可为 AI 意识研究提供模仿无法伪造的证据
AI 导读
据 @NoaWeissAI 表示，她会在 AI 意识研究中优先考虑计算神经科学，因为这类证据是模仿无法伪造的。她引用 @camhberg 未发表的工作称，价值学习 RL 智能体对奖励和惩罚的编码不对称，惩罚相关结构最为丰富，与小鼠伏隔核数据中偏向惩罚的变化相符。
正文
@NoaWeissAI on why she'd prioritize computational neuroscience in AI consciousness research: it's evidence mimicry can't fake.
In unpublished work by @camhberg, value-learning RL agents encoded reward and punishment asymmetrically, with the richest structure around punishment, matching a punishment-heavy shift in mouse nucleus accumbens data.
Link in thread.