On Mon, Apr 5, 2021, 6:13 PM stefan.reich.maker.of.eye via AGI <
[email protected]> wrote:

> I mean yeah, I could eventually do that, but my approach is so different
> I'm not going to score high there at first. Actual AI applications will
> come first. Achieving high compression in the Hutter test seems pretty
> academic to me. What am I supposed to do with a compressor? I want a
> general-purpose AI.
>

Take off the arithmetic encoder and you have a text predictor. Put it back
on and you have a quick evaluation of its accuracy.

But yeah it's not AGI without vision and robotics.


------------------------------------------
Artificial General Intelligence List: AGI
Permalink: 
https://agi.topicbox.com/groups/agi/T29d9a364b5df2085-M87c53e23150cde305c7e9e5d
Delivery options: https://agi.topicbox.com/groups/agi/subscription

Reply via email to