Matthew Green
@matthew_d_green
I teach cryptography at Johns Hopkins. Mostly on BlueSky these days at
加入 January 2010
1.1K 正在关注 158.7K 粉丝
So one thing I’ve heard from multiple researchers in my field is that models seem to get *much* better at solving their specific problems over short periods, even asked in new contexts. Many of them have mentioned that they wonder if they’re training on their inputs.
显示更多
