The problem is only half fulfilled with the enourmous size of the corpus. A huge corpus will only give you plain predictive ability, reasoning and other abilities are not greatly approved.So a simple interaction.Person: My name is BosefusAI: okPerson: What is my name?AI: dunnoNow it is true that
I dont believe "yellow" or "hot" can either be learned verbally.JamesRussell Wallace [EMAIL PROTECTED] wrote: On 8/13/06, Matt Mahoney [EMAIL PROTECTED] wrote: There is no knowledge that you can demonstrate verbally that cannot also be learned verbally. An unusual claim... do you mean all
If dumb models kill smart ones in text compression, then how do you know they are dumb? What is your objective test of "smart"? The fact is that in speech recognition research, language models with a lower perplexity also have lower word error rates.We have "smart" statistical parsers that are 60%
Yellow is the state of reflecting light which is
between two specific frequencies.
Hot is the state of having a temperature above some
set value.
It takes examples to recognize/understand when your
sensory apparatus is reporting one of these states but this is a calibration
issue, not a
Now try that on my daughter or any other 3.5 year old. It doesnt work. :}No, as another poster stated better, there are many things that cant be explained verbally, and need to be "experienced" which is one of my big hangups about AGI in general. There is very little way to have an AI experience
If
dumb models kill smart ones in text compression, then how do you know they are
dumb?
They are dumb
because they are inflexible and always use the same very simple rules.
Fortunately, those "dumb" rules are good enough.
What
is your objective test of "smart"?
Mydefinition of smart
Now
try that on my daughter or any other 3.5 year old. It doesnt work.
:}
Try what? Your daughter has calibrated her
vision and stuck labels on the gauge. What has she learned? That
this range reported by *her* personal vision systemis labeled
yellow.
Now, you want to do this without any
