Scalable Alignment
topic on 1 show · 1 statements across 1 episodes
1 statements about Scalable Alignment, every show
Wang: AI labs underfund interpretability and deepfake detection for new capabilities
“The leading AI labs, you know, they're incentivized very much so to build Incredible new capabilities. But there's a lot of very important technical work and technical research that's been done in areas that are that are not building, you know, cooler capabili…”