You could look at it as horizontal layers of vertical strata. Text processing
layer would be several layers up from the consciousness layer.
Prediction is time asymmetric.
--
Artificial General Intelligence List: AGI
Permalink:
The brain just learns from the past to do better in the future. 4 year olds are
very unwise, even 10 year olds can be easily! Our algorithms are getting fairly
close to predicting the next word like we do in text and image. That's why I
ask you to give examples of why you know the next word.
You guys are starting to make me wonder...
This is one of the coolest papers I've ever seen.
You have to be familiar with the concepts involved and with that type of
math... but they're really synthesizing things nicely, or attempting to do so.
--
I have absolutely no idea what that paper is about
--
Artificial General Intelligence List: AGI
Permalink:
https://agi.topicbox.com/groups/agi/Td2287eb2b142cb0b-M08981d3bb3270e1a61be95c0
Delivery options: https://agi.topicbox.com/groups/agi/subscription
"avoiding ontological claims"
Even without reading the paper, I seriously doubt that they pull this off
if they posit any relevance to reality.
On Thu, Aug 13, 2020 at 3:43 PM John Rose wrote:
> See how nice and clean this is? Refreshing actually:
>
> https://arxiv.org/abs/2007.16138
>
>
>
>
"Religion" is a model .. or really a set of models. The concepts of "science"
and "religion" are a relatively recent invention...
--
Artificial General Intelligence List: AGI
Permalink:
On Thu, Aug 13, 2020, 4:43 PM John Rose wrote:
> See how nice and clean this is? Refreshing actually:
>
> https://arxiv.org/abs/2007.16138
>
No, it doesn't make any predictions that can be tested experimentally. It
is a mathematical model of a religion.
>
>
>
The tools and techniques in the article are pretty amazing.
--
Artificial General Intelligence List: AGI
Permalink:
https://agi.topicbox.com/groups/agi/Td2287eb2b142cb0b-M964424499321c8b2764979b3
Delivery options: