We show applications to long-term outcomes and decision making, developing our works on 'causal parrots' openreview.net/pdf?id=tv46t... and meta-causality openreview.net/pdf?id=J9Vog... .

Thanks to my coauthors @philosotim.bsky.social, @devendradhami.bsky.social and @kerstingaiml.bsky.social! 2/4

We also identified 10 particularly challenging Bongard Problems that none of the models could solve under any setting. The challenge remains wide open!
3 examples of the challenging BPs:

Interestingly, success in solving the BPs (Open Question) doesn't translate to correctly categorizing individual images 👉 the sets of BPs solved in each task are not the same!
This suggests that getting the right final answer doesn’t always mean genuine understanding 🤔

Our evaluation shows the top-performing model (o1) solved 43 out of 100 problems, with the others trailing far behind. There’s still a long way to go for current AI models!

This might be interesting for the same. We provide the concept of meta causal states that can be used to analyze the changes in the causal graph. Work with @moritzwillig.bsky.social @florianbusch.bsky.social @kerstingaiml.bsky.social et al. arxiv.org/abs/2410.13054