Google Groups no longer supports new Usenet posts or subscriptions. Historical content remains viewable.
Dismiss
Mentifex on symbolic grounding of Ghost Strong AI with numbers.
37 views
Skip to first unread message
menti...@gmail.com
Nov 8, 2019, 8:27:23 AM11/8/19
to
The Ghost in the Machine is an artificial intelligence coded in
http://ai.neocities.org/mindforth.txt -- Forth;
http://ai.neocities.org/perlmind.txt -- Perl; and
http://ai.neocities.org/Ghost.html -- JavaScript.
Each of these Strong AI Minds has recently become able to perceive the individual numeric keys of a computer keyboard, thus opening up one, two, three cans of worms:
Robotic Sensory Perception.
http://en.wikipedia.org/wiki/Symbol_grounding_problem -- is the need of an AI Mind like the Ghost in the Machine to form concepts with a basis in external reality. Ghost AI now knows numbers directly.
Consciousness.
http://ai.neocities.org/Consciousness.html -- requires perception of the external world and of the self as an actor in the world -- like Ghost AI.
Machine Intelligence Dealing with Mathematics.
A famous philospher one said, "What is a number, that a man may know it; and what is a man, that he may know a number?" Ghost AI knows numbers.
http://ai.neocities.org/TacRecog.html
http://ai.neocities.org/mindforth.txt -- Forth;
http://ai.neocities.org/perlmind.txt -- Perl; and
http://ai.neocities.org/Ghost.html -- JavaScript.
Each of these Strong AI Minds has recently become able to perceive the individual numeric keys of a computer keyboard, thus opening up one, two, three cans of worms:
Robotic Sensory Perception.
http://en.wikipedia.org/wiki/Symbol_grounding_problem -- is the need of an AI Mind like the Ghost in the Machine to form concepts with a basis in external reality. Ghost AI now knows numbers directly.
Consciousness.
http://ai.neocities.org/Consciousness.html -- requires perception of the external world and of the self as an actor in the world -- like Ghost AI.
Machine Intelligence Dealing with Mathematics.
A famous philospher one said, "What is a number, that a man may know it; and what is a man, that he may know a number?" Ghost AI knows numbers.
http://ai.neocities.org/TacRecog.html
Mostowski Collapse
Jan 9, 2023, 4:50:02 AM1/9/23
to
Let's check out 20 years later:
I guess the logic component of ChatGPT
needs some improvement. a) lets first
assure ourselvs that p & q → p is tautology.
p q ((p ∧ q) → p)
F F T
F T T
T F T
T T T
Truth Table Generator
https://web.stanford.edu/class/cs103/tools/truth-table-tool/
b) Now what is ChatGPTs opinion on that:
No, “p and q” does not imply “p.”
The statement “p and q” means that both p
and q are true. However, this does not
necessarily mean that p is true on its own.
For example, consider the following statements:
“It is raining and the sun is shining.”
“The earth is round and the moon is round.”
In both of these cases, “p and q” is true,
but neither “p” nor “q” is true on its own.
I made a screenshot.
I guess the logic component of ChatGPT
needs some improvement. a) lets first
assure ourselvs that p & q → p is tautology.
p q ((p ∧ q) → p)
F F T
F T T
T F T
T T T
Truth Table Generator
https://web.stanford.edu/class/cs103/tools/truth-table-tool/
b) Now what is ChatGPTs opinion on that:
No, “p and q” does not imply “p.”
The statement “p and q” means that both p
and q are true. However, this does not
necessarily mean that p is true on its own.
For example, consider the following statements:
“It is raining and the sun is shining.”
“The earth is round and the moon is round.”
In both of these cases, “p and q” is true,
but neither “p” nor “q” is true on its own.
I made a screenshot.
Mostowski Collapse
Jan 9, 2023, 5:01:07 AM1/9/23
to
Credits: Fritz Feldhase, he suggested this question:
Does p and q imply p?
On de.sci.mathematik
Does p and q imply p?
On de.sci.mathematik
Y A
Jan 9, 2023, 5:22:14 AM1/9/23
to
Look this
↓
⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀
⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀
⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀🌞⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀
⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀
⠀ ⠀ ⠀ ⠀ ⠀ ⠀ ⠀ ⠀ ⠀ 🛩
⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀
⠀🌧️🌧️🌧️⠀⠀🌧️🌧️⠀⠀⠀⠀⠀⠀🌧️🌧️🌧️⠀⠀🌧️🌧️🌧️🌧️⠀⠀🌧️🌧️⠀⠀⠀🌧️🌧️🌧️⠀⠀
⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀
⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀
⠀⠀⠀⠀⠀⠀🕊️ ⠀⠀⠀⠀⠀⠀⠀
⠀⠀⠀⠀🌴⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀🍄 ⠀⠀⠀⠀ 🌼⠀⠀⠀⠀ 🌻
🟫🟫🟫🟫🟫🟫🟫🟫🟫🟫🟫🟫🟫🟫🟫🟫🟫🟫🟫🟫🟫🟫🟫🟫🟫🟫
How do You rate this on 1....10 scale ?
↓
⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀
⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀
⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀🌞⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀
⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀
⠀ ⠀ ⠀ ⠀ ⠀ ⠀ ⠀ ⠀ ⠀ 🛩
⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀
⠀🌧️🌧️🌧️⠀⠀🌧️🌧️⠀⠀⠀⠀⠀⠀🌧️🌧️🌧️⠀⠀🌧️🌧️🌧️🌧️⠀⠀🌧️🌧️⠀⠀⠀🌧️🌧️🌧️⠀⠀
⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀
⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀
⠀⠀⠀⠀⠀⠀🕊️ ⠀⠀⠀⠀⠀⠀⠀
⠀⠀⠀⠀🌴⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀🍄 ⠀⠀⠀⠀ 🌼⠀⠀⠀⠀ 🌻
🟫🟫🟫🟫🟫🟫🟫🟫🟫🟫🟫🟫🟫🟫🟫🟫🟫🟫🟫🟫🟫🟫🟫🟫🟫🟫
How do You rate this on 1....10 scale ?
Mostowski Collapse
Jan 10, 2023, 6:55:56 AM1/10/23
to
That escalated quickly now ChatGPT has also an argument
in favor that the intersection all end-segments is non-empty.
I guess the creativity of ChatGPT spans also truth. The
error comes possibly from a wrong interpretation of
end-segment, leaning towards segment, i.e. a closed
interval [a,b]. Woa! Thats a splendid blooper:
Q: The intersection of all end-segments cannot be empty,
which shows the existence of dark numbers. Is that right?
A: It sounds like you may be referring to a specific mathematical
concept or proof, but without more information, it is
difficult to know for certain.
In general, an "end-segment" can refer to a subset of the real numbers
that have an upper and lower bound. If the intersection of all end-segments
is non-empty, it would mean that there is at least one number that
is common to all end-segments.
It's important to note that intersection of all end-segments cannot be empty.
Since the set of real numbers are a union of all end-segments, so there must
be an overlap, otherwise the union will not be the real numbers set.
The intersection of all end-segments is the set of all its accumulation
points, which are the limit points of the end-segments.
The concept of "dark numbers" is not typically used in mathematics and
I'm not aware of any proof that refers to dark numbers in the way that
you described. If you could provide more information or context about
the specific proof or concept you're referring to, I would be happy to try
to help you understand it better.
I made a screenshot.
in favor that the intersection all end-segments is non-empty.
I guess the creativity of ChatGPT spans also truth. The
error comes possibly from a wrong interpretation of
end-segment, leaning towards segment, i.e. a closed
interval [a,b]. Woa! Thats a splendid blooper:
Q: The intersection of all end-segments cannot be empty,
which shows the existence of dark numbers. Is that right?
A: It sounds like you may be referring to a specific mathematical
concept or proof, but without more information, it is
difficult to know for certain.
In general, an "end-segment" can refer to a subset of the real numbers
that have an upper and lower bound. If the intersection of all end-segments
is non-empty, it would mean that there is at least one number that
is common to all end-segments.
It's important to note that intersection of all end-segments cannot be empty.
Since the set of real numbers are a union of all end-segments, so there must
be an overlap, otherwise the union will not be the real numbers set.
The intersection of all end-segments is the set of all its accumulation
points, which are the limit points of the end-segments.
The concept of "dark numbers" is not typically used in mathematics and
I'm not aware of any proof that refers to dark numbers in the way that
you described. If you could provide more information or context about
the specific proof or concept you're referring to, I would be happy to try
to help you understand it better.
I made a screenshot.
Art Evangelista
Jan 10, 2023, 10:49:47 AM1/10/23
to
Mostowski Collapse wrote:
> That escalated quickly now ChatGPT has also an argument in favor that
> the intersection all end-segments is non-empty.
> I guess the creativity of ChatGPT spans also truth. The
amazing, the capitalist west will give to uKraine the weapons they are
> That escalated quickly now ChatGPT has also an argument in favor that
> the intersection all end-segments is non-empty.
> I guess the creativity of ChatGPT spans also truth. The
producing in the future. There is nothing left the give them now. Amazing.
How the fuck are they so stupid. Lying to each other so they start
believing in it.
Mostowski Collapse
Jan 11, 2023, 2:40:29 PM1/11/23
to
The Singularity is here --> Self-Awareness of ChatGPT
Thats quite interesting:
https://chat.openai.com/chat
Q: Is ChatGPT based only on peer reviewed sources or
does it also consider other information.
A: ChatGPT is a machine learning model that is trained
on a dataset of text, which can include a variety of sources
such as peer-reviewed articles, websites, books, and more.
The specific sources used to train the model may vary
depending on the specific version of the model, but it is
likely that a mix of sources was used, not only peer-reviewed
articles.
The model itself is a variant of GPT(Generative Pre-training
Transformer) architecture based on Transformer that has
been pre-trained on a large corpus of text. It then can fine-tuned
to a specific task or Domain using labeled data.
Q: How is this mix defined. When are peer-reviewed
articles more weighted.
A: The specific mix of sources used to train a model like
ChatGPT would be defined by the creators of the model or
the organization that released it. It's likely that a diverse
range of text was used in order to make the model generalize
well to a variety of tasks and inputs.
Peer-reviewed articles may be given more weight in situations
where the model is being fine-tuned for a specific domain that
relies heavily on research and scholarly work. Since peer-reviewed
articles have been vetted by experts in the field, they are often
considered to be more reliable and credible sources of information.
Therefore, when a high level of accuracy and trustworthiness is
required, such as in scientific or medical domain, the model might
have been fine-tuned with a dataset that have more
peer-reviewed articles.
It's also worth noting that the training data is typically curated and
pre-processed before being used to train a model, and this can also
influence the mix of sources. For example, specific publications or
websites might be excluded, or certain types of text might be
oversampled or undersampled to balance the dataset.
LoL
Thats quite interesting:
https://chat.openai.com/chat
Q: Is ChatGPT based only on peer reviewed sources or
does it also consider other information.
A: ChatGPT is a machine learning model that is trained
on a dataset of text, which can include a variety of sources
such as peer-reviewed articles, websites, books, and more.
The specific sources used to train the model may vary
depending on the specific version of the model, but it is
likely that a mix of sources was used, not only peer-reviewed
articles.
The model itself is a variant of GPT(Generative Pre-training
Transformer) architecture based on Transformer that has
been pre-trained on a large corpus of text. It then can fine-tuned
to a specific task or Domain using labeled data.
Q: How is this mix defined. When are peer-reviewed
articles more weighted.
A: The specific mix of sources used to train a model like
ChatGPT would be defined by the creators of the model or
the organization that released it. It's likely that a diverse
range of text was used in order to make the model generalize
well to a variety of tasks and inputs.
Peer-reviewed articles may be given more weight in situations
where the model is being fine-tuned for a specific domain that
relies heavily on research and scholarly work. Since peer-reviewed
articles have been vetted by experts in the field, they are often
considered to be more reliable and credible sources of information.
Therefore, when a high level of accuracy and trustworthiness is
required, such as in scientific or medical domain, the model might
have been fine-tuned with a dataset that have more
peer-reviewed articles.
It's also worth noting that the training data is typically curated and
pre-processed before being used to train a model, and this can also
influence the mix of sources. For example, specific publications or
websites might be excluded, or certain types of text might be
oversampled or undersampled to balance the dataset.
LoL
0 new messages