新论文称约90%神经元功能清晰，可解释性研究引发学界争论
Is AI interpretability close to a breakthrough? A new essay has researchers divided
有研究者说90%的神经元功能都能读懂，如果属实，查模型有没有撒谎可以直接看电路，学界正在吵这个说法靠不靠谱。
一篇新论文提出神经网络比此前假设的更易解读，约90%的神经元承担清晰功能。如果这一论断成立，AI安全研究可以直接从模型电路中发现欺骗或危险行为。学界目前对这一论点是否成立仍存在分歧。
Is AI interpretability close to a breakthrough? A new essay has researchers divided
Neural networks may be much easier to read than researchers assumed, with about 90 percent of neurons serving a clear function. That would be big news for AI safety research, since deception or dangerous behavior could be spotted directly in a model's circuits. Researchers are still debating whether the thesis holds up. The article Is AI interpretability close to a breakthrough? A new essay has researchers divided appeared first on The Decoder .
