I thought I was not going to see too many negative comments here, yet I was mistaken. I thought if it's not LLM, people would have a more nuanced take and could look at the research with an open mind. The examples on the website are probably cherry-picked, but progress is really nice compared to Genie 2.
It's a nice step towards gains in embodied AI. Good work, DeepMind.
A lot of the negativity around this post is about the fact that there’s no demo and no open weights, which is Correct Negativity. Like don’t get me wrong, it would be cool for something like this to exist, but I’ve generally learned not to trust AI companies’ descriptions of their models until someone (or I) can actually get their hands on it and see if it’s usable at all. A description of a model that isn’t going to be released to the public isn’t very interesting to me.
It's a nice step towards gains in embodied AI. Good work, DeepMind.