Can anyone point me to models that look like they might actually be useful in moving towards AGI? I feel like I have a basic understanding of the transformer architecture, and multiplying X tokens in a sliding window across a set of static matrices to produce 1 new token does not look like a path to AGI.
Yes, the complex feature extraction is impressive. But are there any models that, I don't know, are more dynamic? Have a working memory? Have a less limited execution path?
Yes, the complex feature extraction is impressive. But are there any models that, I don't know, are more dynamic? Have a working memory? Have a less limited execution path?