提出以基于困惑度的指标作为通用智能的共享基准,预测进入0.68-0.7对数困惑度窗口后将涌现变革性能力。同时指出主流对齐审计形式将进一步退化,评估与训练感知度将显著增加。
Jakub Pachocki:
'Given that the main way new surprising capabilities emerge is by progress on compression, a measure rooted in perplexity could give us a shared benchmark for general intelligence, regardless of the degree of automation of the development process. Extrapolating from recent progress, we should expect further transformative capabilities as we enter the ~0.68-0.7 log-perplexity window. I don’t know what those capabilities will be, and we may not be testing for them today.
At the same time, we should also expect further degradation in currently dominant forms of alignment auditing and further increases in evaluation and training awareness.'
来源:Andrew Curran · x.com