• 0 Posts
  • 36 Comments
Joined 3 years ago
cake
Cake day: June 10th, 2023

help-circle










  • I feel like her sacrificial decision to give him this (ultimately meaningless) symbolic token in exchange for the potential of peace for her country is showing why she deserved the Peace Prize in the first place. If handing it over makes Trump chill the hell out about working with Venezuela’s succession, it will have been worth it.

    (This situation is obviously batshit insane and it’s pathetic that he’s extorting her, but at least she’s trying to use all her resources available to manipulate this mad king and sue for peace - if this Nobel Prize was driving his hatred, it’s best to sacrifice it I guess. Especially since the actual honor is non-transferrable LMAO)





  • This method is definitely a great way to achieve some degree of explainability for images, but it is based on the assumption that nearby pixels will have correllated meanings. When AI is making connections between far-away features, or worse, in a feature space that cannot be readily visualized like images can, it can be very hard to decouple the nonlinear outputs into singular linear features. While AI explainability has come a long way in the last few years, the decision-making processes of AI are so different from human thought that even when it can “show its work” by showing which neurons contributed to the final result, it doesn’t necessarily make any intuitive sense to us.

    For example, an image-identification AI might identify subtle lens blur data to determine the brand of camera that took a photograph, and then use that data to make an educated guess about which country the image was taken in. It’s a valid path of reasoning. But it would take a lot of effort for a human analyst to notice that the AI is using this process to slightly improve its chances of getting the image identification correct, and there are millions of such derived features that combine in unexpected ways, some logical and some irrationally overfitting to the training data.