#neural

Humans can (almost) natively read neural network weights

Takehi et al. report that GPT-6-Astra can intuit the functions of neural networks by performing static analysis of the weights. I argue that, for at least two of these experiments, this is much more a feat of numerical gestalt than of mechanistic understanding. In the first experiment, Astra is given the weights of 4 identically-sized neural networks, each trained to play a different basic video game. It is asked to identify, without running the network or using any tools, the game being played, as well as make some observations about the network itself, how the agent in the game gains reward,

LessWrong · EN

逆境会改变大脑

这篇文章《A stable and replicable neural signature of lifespan adversity in the adult brain》在《Nature Neuroscience》上发表，讲述了一项纵向研究，研究人员通过对约170人的一生数据及其大脑结构的检视，发现逆境（如母亲怀孕期吸烟，受虐待等负面事件）会导致大脑广泛的形态变化，这种影响与生逆境类型和患者大脑特定区域有关。研究结果显示，这种逆境对大脑结构的影响是可持续且稳定的，逆境不仅改变了大脑结构，而且可能引起持续的焦虑症状，有助于预测谁更有可能患上精神障碍，这为精神健康的干预和治疗提供了新的理论依据。逆境不仅是社会和心理问题，更是生物学问题。我们需要对逆境的影响进行更多重视，寻求有效策略减轻其对个人和家庭的长期影响。同时，研究团队开源了用于预测临床神经科学的工具包，旨在推动此领域的进一步发展。

轶哥博客 · ZH

Show HN: Watch an LLM program a neural net's weights instead of training it

A lab where Opus brews smart pills for a tiny JS neural net by writing its weights directly (weight-space programming) - lusob/model-booster

Show HN · EN