placement: 'bottom',
interaction, evaluation commands, and a poor man's SLIME/SLY setup
。关于这个话题，新收录的资料提供了深入分析
The optimal configuration was $(45, 52)$: layers 0 through 51 run first, then layers 45 through 79 run again. Layers 45 to 51 execute twice. Seven extra layers, near the middle of the 80-layer stack, bringing the total parameter count from 72B to 78B. Every extra layer is an exact copy of an existing one. No new weights or training, just the model repeating itself.
Many in the technology industry have been captivated by the computer-led dialogue on Moltbook's forums, but it has also fuelled cyber security and ethical concerns regarding AI's autonomy.