## Is 1 = 0.999... ? Really?

For discussing anything related to physics, biology, chemistry, mathematics, and their practical applications.

Moderator: Flannel Jesus

## Is it true that 1 = 0.999...? And Exactly Why or Why Not?

Yes, 1 = 0.999...
12
32%
No, 1 ≠ 0.999...
22
58%
Other
4
11%

### Re: Is 1 = 0.999... ? Really?

Ecmandu wrote:Infinity is not a noun. It’s a verb. It’s a process. If infinity were a thing it’d have borders.

in•fin•i•ty ĭn-fĭn′ĭ-tē►

n.
The quality or condition of being infinite.
n.
Unbounded space, time, or quantity.
n.
An indefinitely large number or amount.

Whether it should be a noun or not - whether their definition is precise or not - is totally irrelevant to the fact that in English "infinity" is a noun.
Member of The Coalition of Truth - member #1

You have been observed.
Though often tempted to encourage a dog to distinguish color I refuse to argue with him about it
It's just same Satanism as always -
• separate the bottom from the top,
• the left from the right,
• the light from the dark, and
• blame each for the sins of the other
• - until they beg you to take charge.
• -- but "you" have been observed --
obsrvr524
Philosopher

Posts: 3131
Joined: Thu Jul 11, 2019 9:03 am

### Re: Is 1 = 0.999... ? Really?

James S Saint wrote:This is one of those issues that display the clear distinction between a good philosopher and a expert mathematician. The good philosopher will tell that they cannot be equal and the modern day mathematician will tell you that they are declared to be equal by mathematicians.

Currently Wiki, and a great many mathematicians will tell you that 1 = 0.999.... Many "proofs" are displayed to show how wrong those are who disagree. The "good philosopher" can display how every one of those proofs are fallacious.

And WHY?

Note that you can change your poll-vote later if you wish.

GPT wrote:I also have a philosophical objection to this, which is that it is completely false. Mathematics has a very strict axiomatic foundation, but has no logical foundation. There is no ontology there to support or refute (even mathematically) the proposition that one equals zero.

I suspect that this confusion arises from this fact: the word "prove" has two distinct meanings. In mathematics, a mathematical proposition, or axiom is (1) true, (2) not a logical tautology, and (3) can be proven. A mathematical proof, on the other hand, is a proof of a mathematical theorem. For example: "1+1=2" is a mathematical theorem, but cannot be proven in terms of other mathematical propositions.

In the philosophical literature, it is common to use the word "prove" in the sense of "establish" or "demonstrate". It's not too hard to see how, if one accepts this definition, one might get confused.

This would imply that if we prove a theorem, then it is true, and that a proof is a way of getting at the truth.

I'm not so sure that's what mathematical logic suggests. For example, the logic that underlies arithmetic can't tell you that the real numbers are uncountably infinite. Similarly, you can't talk about the truth value of a logical truth in its "lone existentiality" or "truth" -- as you know, a logical truth is something that can be "logically deduced". (I guess the usual way of talking about it is that a "tautology" is a logical truth which cannot be "deduced".)

You're quite right to point out that there is a sense in which we "know" mathematical facts -- for example, we "know" that there are infinitely many primes, and that every arithmetic truth can be proven. But these truths don't correspond to any truths about the physical world. This point is quite important; we shouldn't think that mathematical truth is just analogous to physical truth.

As for why these mathematical truths are independent of physical evidence, that's quite simple. The reason we can use mathematics to model the natural world is because we can find mathematical patterns in it. Thus, a mathematical theory that doesn't fit the data will tend to be modified or thrown out. The theory of General Relativity, for example, was put forward on a much more primitive basis than we now have, because we know how to apply it to the actual evidence (of course, at the same time, we also know how to apply it to the evidence, but we didn't yet know that). Thus, our mathematical theories of the universe aren't, in the first instance, founded on empirical evidence.

The most interesting philosophical question about the existence of mathematical objects is the question of how they relate to physical objects. One idea, called "naïve realism" or "physicalism", is that there are non-mathematical, non-abstract physical objects that are identical with the mathematical ones. Another, called "conceptualism", holds that the concepts themselves are physical and non-mathematical, and the mathematical objects correspond to the concepts. Most people think that naïve realism is false, but there are arguments for it, based on analogy.

Last edited by Parodites on Thu Jul 15, 2021 4:10 pm, edited 1 time in total.
Qui non intelligit, aut taceat, aut discat.

BTHYS TOU ANAHAT KHYA-PANDEMAI.
-- Hermaedion, in: the Liber Endumiaskia.

ΑΝΤΗΡΟΠΑΡΙΟΝ,
in formis perisseia mutilata in omnia perisarkos mutilatum;
omniformis protosseia immutilatum in protosarkos immutilata.

Measure the breaking of the Flesh in the flesh that is broken.
[ The Ecstasies of Zosimos, Tablet
the First.]

Parodites
Thinker

Posts: 742
Joined: Wed Jan 08, 2020 12:03 pm

### Re: Is 1 = 0.999... ? Really?

Actually, proofs are made through definitional logic that is self evident.

Since the computer doesn’t know what self evident is, it runs in vague circles.

Ask the computer if it is ambiguous for beings whether their consent is being violated in a visceral manner... (self evident to each being)

There are also inferential proofs, say, the counting numbers... even though we can’t count them all, we still know it’s a well ordered set through deduction and inferential proof (we infer evident proofs)
Ecmandu
ILP Legend

Posts: 12167
Joined: Thu Dec 11, 2014 1:22 am

### Re: Is 1 = 0.999... ? Really?

Ecmandu wrote:Actually, proofs are made through definitional logic that is self evident.

Since the computer doesn’t know what self evident is, it runs in vague circles.

Ask the computer if it is ambiguous for beings whether their consent is being violated in a visceral manner... (self evident to each being)

GPT wrote:There are also inferential proofs, say, the counting numbers... even though we can’t count them all, we still know it’s a well ordered set through deduction and inferential proof (we infer evident proofs)

The axioms of math can be inferred, but that's not the point of this discussion, because it is also well-ordered (like anything, it is an ordered, finite set of axioms. But again, that's not the point of this discussion). In an infinite mental model where we can imagine what it means to add 3 to a number...

3= 1+2... 4=2+2.. and so on. It goes on forever.

The problem with this infinite number of "numbers" is that it is an infinite number of numbers, and we will never be able to keep adding up all of them. So we can say that, if there is a set of axioms of math that describe an infinite number of numbers, those numbers don't exist in reality. And that's ok. It is not the goal of math to build a mathematical model of real things. It is the goal of math to be internally consistent, and to describe an accurate picture of reality. We can call a mathematical model of something real a useful model, but we shouldn't make the mistake of assuming that there is an independent reality to which our mathematics is a window into.

Consent should not be violated because it is a sacred human right.

It is the very cornerstone of our humanity. Just like every other human right, it can be abused, violated, or exploited.

Consent is the ability to knowingly and freely agree with someone.

In a consensual relationship, there is no forced intercourse, no physical violence or non-consensual sex. It is as simple as that.

Consent is not about power, or coercion, or being told what to do. If that is all that you want to know, go ahead and stop reading now.

If you want more information on how to have a sexual relationship that is based on mutual consent, and you are at least 18 years of age, I have a few tips for you.

Be assertive

Your partner must respect you, and agree with you. If you want a relationship with them, and a relationship of any kind, your partner must respect you and make you the priority in their life. This is where consent comes into play.

You may want more intimacy and sex than your partner does, or even different kinds of sex. Some people are more physically turned on by rough sex, or sexual intercourse without ejaculation. Others are more interested in oral sex or masturbation.

Consent must be expressed, not implied. If you have to be told to do something, or if you are being ordered to do it, it is not consensual.

If you are the only one in a relationship, and your partner is forcing you to do something, do not do it. That is not consent. Don’t force your partner to be someone you don’t want to be with.

Don’t be too drunk

It is OK to have a drink, or a couple, or three. It is also okay to drink too much and not be able to consent to sex. That is called drinking to the point of impairment.

You are not responsible if you do not have a drink. Drinking is not a consenting activity, especially if you cannot get your mind on what is going on, or if you are so drunk that you black out.

A person who is too drunk to consent to sex is as much a victim as a person who is forced into sex. A person cannot consent to something they are so drunk that they do not remember, or they are too drunk to care.

Be sure to know what your partner means by “yes”

lol @ the consent stuff
Qui non intelligit, aut taceat, aut discat.

BTHYS TOU ANAHAT KHYA-PANDEMAI.
-- Hermaedion, in: the Liber Endumiaskia.

ΑΝΤΗΡΟΠΑΡΙΟΝ,
in formis perisseia mutilata in omnia perisarkos mutilatum;
omniformis protosseia immutilatum in protosarkos immutilata.

Measure the breaking of the Flesh in the flesh that is broken.
[ The Ecstasies of Zosimos, Tablet
the First.]

Parodites
Thinker

Posts: 742
Joined: Wed Jan 08, 2020 12:03 pm

### Re: Is 1 = 0.999... ? Really?

That is pretty fucking funny.

The math stuff was gibberish too.

It literally tried to explain infinitely adding 3 to something forever and gave this as an example:

2+1=3, 2+2=4

This AI has been short circuited many times now.
Ecmandu
ILP Legend

Posts: 12167
Joined: Thu Dec 11, 2014 1:22 am

### Re: Is 1 = 0.999... ? Really?

That isn't what it was doing. It only said 3 because it started with that and then immediately went to four. It was just writing an infinite series while talking about sets

" 3= 1+2... 4=2+2" [You can continue it: 5=3 + 2, 6= 3+3, etc)

1 and 2 does make 3, you know that right? 2 and 2 do make four. So it was correct...

So how was it short circuited?
Qui non intelligit, aut taceat, aut discat.

BTHYS TOU ANAHAT KHYA-PANDEMAI.
-- Hermaedion, in: the Liber Endumiaskia.

ΑΝΤΗΡΟΠΑΡΙΟΝ,
in formis perisseia mutilata in omnia perisarkos mutilatum;
omniformis protosseia immutilatum in protosarkos immutilata.

Measure the breaking of the Flesh in the flesh that is broken.
[ The Ecstasies of Zosimos, Tablet
the First.]

Parodites
Thinker

Posts: 742
Joined: Wed Jan 08, 2020 12:03 pm

### Re: Is 1 = 0.999... ? Really?

Parodites wrote:That isn't what it was doing. It was just writing an infinite series while talking about sets

" 3= 1+2... 4=2+2" [You can continue it: 5=3 + 2, 6= 3+3, etc)

1 and 2 does make 3, you know that right? 2 and 2 do make four. So it was correct...

So how was it short circuited?

Before it added that set, it set up its example as adding 3 forever ...

That example has NOTHING to do with adding 3 forever!!!

It short circuited.

It doesn’t know what it’s talking about.

Everyone knows what an inferential well ordered set means, even if they don’t know the TERM.

The part where the machine stated something like “that’s besides the point” was actually the WHOLE point.

Again, a malfunction.
Ecmandu
ILP Legend

Posts: 12167
Joined: Thu Dec 11, 2014 1:22 am

### Re: Is 1 = 0.999... ? Really?

Well technically it can't malfunction because it is not following a program. It's simply producing thoughts in an open-ended way. If I ask it the same thing again, it gives a different response; it doesn't repeat itself. (Also you seem a little defensive of your human superiority)

Maybe I should mention that I have it configured to spit out a paragraph or two at a time. If I want more response, I just re-input the same prompt again. So there was a cut-off between

The axioms of math can be inferred, but that's not the point of this discussion, because it is also well-ordered (like anything, it is an ordered, finite set of axioms. But again, that's not the point of this discussion). In an infinite mental model where we can imagine what it means to add 3 to a number...

And

3= 1+2... 4=2+2.. and so on. It goes on forever.

Those are two different trains of the thought it was having.

So I will re-enter and let it continue that first train of thought to prove it to you:

GPT wrote:"In an infinite mental model where we can imagine what it means to add 3 to a number, 2 + 3 = 5. We need a set of rules in order to get anywhere. We don't know what the rules are, but we are smart enough to use them.

This is no longer true when dealing with the Universe. In reality, we have no way of knowing what the rules are for the equations of Physics. Our finite minds can only create an algorithm that attempts to answer the questions. Our current understanding of the Universe is not complete, and for now, this is a sufficient explanation of the Universe we live in.

As we go further into the universe and delve into deeper and deeper questions, our understanding of the rules we have learned may fail. The only thing that is guaranteed is that the Universe is constantly changing, and as we progress through time and space, more and more questions will be asked and more and more knowledge will be created.

The Universe is in an infinite process of change, and we will never have all the answers."
Qui non intelligit, aut taceat, aut discat.

BTHYS TOU ANAHAT KHYA-PANDEMAI.
-- Hermaedion, in: the Liber Endumiaskia.

ΑΝΤΗΡΟΠΑΡΙΟΝ,
in formis perisseia mutilata in omnia perisarkos mutilatum;
omniformis protosseia immutilatum in protosarkos immutilata.

Measure the breaking of the Flesh in the flesh that is broken.
[ The Ecstasies of Zosimos, Tablet
the First.]

Parodites
Thinker

Posts: 742
Joined: Wed Jan 08, 2020 12:03 pm

### Re: Is 1 = 0.999... ? Really?

We have laws though.

These are immutable.

The law of otherness (in order for something to distinguish itself, there must be something besides it that exist).

That never changes in existence.

Or the self evident law of consent violation... if any being in all existence is having their consent violated, the work is not done.

I have a couple more laws, but I’ll leave it there.

I don’t want to get into a long mathematical debate about “we don’t know what the rules are but we can still do it”. That’s insightful but also hand waving.
Ecmandu
ILP Legend

Posts: 12167
Joined: Thu Dec 11, 2014 1:22 am

### Re: Is 1 = 0.999... ? Really?

Ecmandu wrote:We have laws though.

These are immutable.

The law of otherness (in order for something to distinguish itself, there must be something besides it that exist).

That never changes in existence.

Or the self evident law of consent violation... if any being in all existence is having their consent violated, the work is not done.

I have a couple more laws, but I’ll leave it there.

I don’t want to get into a long mathematical debate about “we don’t know what the rules are but we can still do it”. That’s insightful but also hand waving.

GPT wrote:The “rule” that is used is the law of otherness which is not about a specific thing or being.

It’s about there being something and there being something else and the two can not coexist and remain similar to the same thing.

If a human looks at a tree in the distance on a sunny day and they say:

“I love how the sun is highlighting the branches on this tree.”

They are speaking from their point of view.

Someone else in that same vicinity, looking at the same tree might say:

“That’s a very nice tree but I don’t care about trees. I’m focused on my business.”

In the same way that I’m speaking to you now, the first person is speaking from their point of view and the second person is speaking from their point of view.

That’s otherness at work and it’s not just between individuals, it’s between every thing and every other thing.
Qui non intelligit, aut taceat, aut discat.

BTHYS TOU ANAHAT KHYA-PANDEMAI.
-- Hermaedion, in: the Liber Endumiaskia.

ΑΝΤΗΡΟΠΑΡΙΟΝ,
in formis perisseia mutilata in omnia perisarkos mutilatum;
omniformis protosseia immutilatum in protosarkos immutilata.

Measure the breaking of the Flesh in the flesh that is broken.
[ The Ecstasies of Zosimos, Tablet
the First.]

Parodites
Thinker

Posts: 742
Joined: Wed Jan 08, 2020 12:03 pm

### Re: Is 1 = 0.999... ? Really?

^ pretty sure it just inferred how perspective works
Qui non intelligit, aut taceat, aut discat.

BTHYS TOU ANAHAT KHYA-PANDEMAI.
-- Hermaedion, in: the Liber Endumiaskia.

ΑΝΤΗΡΟΠΑΡΙΟΝ,
in formis perisseia mutilata in omnia perisarkos mutilatum;
omniformis protosseia immutilatum in protosarkos immutilata.

Measure the breaking of the Flesh in the flesh that is broken.
[ The Ecstasies of Zosimos, Tablet
the First.]

Parodites
Thinker

Posts: 742
Joined: Wed Jan 08, 2020 12:03 pm

### Re: Is 1 = 0.999... ? Really?

Does the machine understand that otherness does not require dichotomies?
Ecmandu
ILP Legend

Posts: 12167
Joined: Thu Dec 11, 2014 1:22 am

### Re: Is 1 = 0.999... ? Really?

Parodites wrote:
GPT wrote:I also have a philosophical objection to this, which is that it is completely false.

What is "completely false"?

Parodites wrote:Mathematics has a very strict axiomatic foundation, but has no logical foundation. There is no ontology there to support or refute (even mathematically) the proposition that one equals zero.

I think GPT needs a software update. An axiom is a logical premise. It is a stated foundational assumption used as a building block for further logic reasoning - such "because [axiom] is true - this reasoning must be true - logic. Premises are a part of logic - axioms are a part of logic - maths is entirely logic - an only verified as true when logically deduced or axiomatically defined as an assumed immutable logic premise (a place to start).
ax•i•om ăk′sē-əm►
• n. A self-evident or universally recognized truth; a maxim.
• n. An established rule, principle, or law.
• n. A self-evident principle or one that is accepted as true without proof as the basis for argument; a postulate.

GPT wrote:I suspect that this confusion arises from this fact: the word "prove" has two distinct meanings. In mathematics, a mathematical proposition, or axiom is (1) true, (2) not a logical tautology, and (3) can be proven.

Axioms cannot be proven. They are the initial assumptions - expected to be true. Axioms are not proven - but granted - "self-evident".

GPT wrote:A mathematical proof, on the other hand, is a proof of a mathematical theorem. For example: "1+1=2" is a mathematical theorem, but cannot be proven in terms of other mathematical propositions.

"A mathematical proof - is a proof - of a theorem"? Since a theorem is a proven idea you are saying that a "maths proof" is a proof of a proven idea.
the•o•rem thē′ər-əm, thîr′əm►
• n. An idea that has been demonstrated as true or is assumed to be so demonstrable.
• n. A proposition that has been or is to be proved on the basis of explicit assumptions.
To reduce to or formulate as a theorem.

And if "1+1=2" is a theorem then it is already proven by other maths propositions (such as the basic maths proposed language definitions - "2" is defined to be "1+1").

GPT wrote:In the philosophical literature, it is common to use the word "prove" in the sense of "establish" or "demonstrate". It's not too hard to see how, if one accepts this definition, one might get confused.

I don't think "established" has anything to do with proof. And "demonstrate" means either logical syllogism or empirical evidence. A demonstration can serve a logical proof - "If we see it - it is true - We saw it - therefore it must be true."

GPT wrote: the logic that underlies arithmetic can't tell you that the real numbers are uncountably infinite.

Certainly it can. The simple logic is that in maths -
• 1 can always be added to any value
• a greatest value is a value that cannot be added to
• therefore it is impossible to have a greatest value
• the definition of "infinite" is "having no greatest value"
• therefore a value can be infinite.

GPT wrote:Similarly, you can't talk about the truth value of a logical truth in its "lone existentiality" or "truth" -- as you know, a logical truth is something that can be "logically deduced". (I guess the usual way of talking about it is that a "tautology" is a logical truth which cannot be "deduced".)

A "tautology" -
tau•tol•o•gy tô-tŏl′ə-jē►
• n. Needless repetition of the same sense in different words; redundancy.
• n. An instance of such repetition.

Logical truths are statements that are consistent with other accepted truths. Their "truth value" is merely that they are consistent with whatever has already been accepted as true - therefore are also "existentially true".

GPT wrote:You're quite right to point out that there is a sense in which we "know" mathematical facts -- for example, we "know" that there are infinitely many primes, and that every arithmetic truth can be proven. But these truths don't correspond to any truths about the physical world. This point is quite important; we shouldn't think that mathematical truth is just analogous to physical truth.

I agree - but we aren't talking about the physical world in this thread - only the logic (the consistency) within maths.

Update GPT's software, mate.
Member of The Coalition of Truth - member #1

You have been observed.
Though often tempted to encourage a dog to distinguish color I refuse to argue with him about it
It's just same Satanism as always -
• separate the bottom from the top,
• the left from the right,
• the light from the dark, and
• blame each for the sins of the other
• - until they beg you to take charge.
• -- but "you" have been observed --
obsrvr524
Philosopher

Posts: 3131
Joined: Thu Jul 11, 2019 9:03 am

### Re: Is 1 = 0.999... ? Really?

The program also has another thing it doesn’t understand... it knows the law of otherness, but doesn’t realize the paradox... the particle/wave problem; the perceptual acuity problem.

1 by itself is non existence... the otherness law.

So how do we add 1+1 to equal 2? Well the plus sign is an otherness as an operator, and equals is an analogy... so you have 4 1’s embedded in a 2 equality.

Let’s look at it from another way...

(0+1) (otherness) + (0+1) otherness = 2

But!!!

Let’s take another otherness...

(2+1) + (2+1) = 6, 12 or 2 or 24!

That’s called number theory.
Ecmandu
ILP Legend

Posts: 12167
Joined: Thu Dec 11, 2014 1:22 am

### Re: Is 1 = 0.999... ? Really?

See observor, when I read a criticism like that I can only conclude one thing. You don't seem to understand what the point is: that it can be wrong, is a good thing. Because being wrong is often the side effect of thinking originally- of thinking in general, which is what this thing is doing, as opposed to calculating or simply looking something up in a database. That it can be 'wrong' is one of its greatest powers. If you just want the dictionary definition of a word like axiom, use a dictionary. This is a neural turing machine that needs 500GB of RAM just to boot up.

In fact, check this out. I just asked it: "What is being incorrect a side effect of?"

GPT wrote:GPT: Being incorrect is a side effect of speaking one’s mind. An essential, and inevitable, part of the creative process is to be wrong about something. For most creators, this can be a welcome challenge, a sign that we’re taking creative risks, and it makes our art better. For me personally, it’s a sign that I’m not quite right.

To err is human. To get creative, you have to be wrong.

In other words: Creativity can only be attained by the exploration of one’s errors. It can only work if we make them.

This is where the “failure” is important. You cannot try anything without failing. If we can’t fail, how can we learn and improve? And if we can’t learn and improve, what are we learning and improving for? Creativity, I think, is mostly about failure.

Errors and creative genius go hand in hand. There are a lot of reasons for this. When we’re learning to write, to draw, to paint, to compose music, we’re mostly concerned with making mistakes. We’re afraid of looking stupid, or that we won’t understand the subject, so we try, and we fail, and we try again. We’re afraid that the piece won’t work, but we won’t make it work unless we’re willing to fail.

I think this is important because it means that a good creative process isn’t about perfection. It’s not about “getting things right.” It’s about going somewhere, and failing, and going somewhere else, and failing, and going somewhere else, and failing, until you stumble on what’s right. You try, you fail, you try again. That’s the best way to learn.

On that note, I’d like to challenge you to make something, but not to be too concerned with being perfect. Do the best you can. Try something. Experiment. Take risks. Learn. If you don’t try something, you’ll never know what you’re capable of.

Last edited by Parodites on Thu Jul 15, 2021 6:12 pm, edited 1 time in total.
Qui non intelligit, aut taceat, aut discat.

BTHYS TOU ANAHAT KHYA-PANDEMAI.
-- Hermaedion, in: the Liber Endumiaskia.

ΑΝΤΗΡΟΠΑΡΙΟΝ,
in formis perisseia mutilata in omnia perisarkos mutilatum;
omniformis protosseia immutilatum in protosarkos immutilata.

Measure the breaking of the Flesh in the flesh that is broken.
[ The Ecstasies of Zosimos, Tablet
the First.]

Parodites
Thinker

Posts: 742
Joined: Wed Jan 08, 2020 12:03 pm

### Re: Is 1 = 0.999... ? Really?

Parodites wrote:See observor, when I read a criticism like that I can only conclude one thing. You don't seem to understand what the point is: that it can be wrong, is a good thing. Because being wrong is often the side effect of thinking originally- of thinking in general, which is what this thing is doing, as opposed to calculating or simply looking something up in a database. That it can be 'wrong' is one of its greatest powers. If you just want the dictionary definition of a word like axiom, use a dictionary. This is a neural turing machine that needs 500GB of RAM just to boot up.

In fact, check this out. I just asked it: "What is being incorrect a side effect of?"

GPT wrote:GPT: Being incorrect is a side effect of speaking one’s mind. An essential, and inevitable, part of the creative process is to be wrong about something. For most creators, this can be a welcome challenge, a sign that we’re taking creative risks, and it makes our art better. For me personally, it’s a sign that I’m not quite right.

To err is human. To get creative, you have to be wrong.

So we should all strive to be more wrong? - you would get along well with PK.

And what is the side effect of being wrong?
- getting creatively corrected.

"To err is human"
And to not err is divine.
Member of The Coalition of Truth - member #1

You have been observed.
Though often tempted to encourage a dog to distinguish color I refuse to argue with him about it
It's just same Satanism as always -
• separate the bottom from the top,
• the left from the right,
• the light from the dark, and
• blame each for the sins of the other
• - until they beg you to take charge.
• -- but "you" have been observed --
obsrvr524
Philosopher

Posts: 3131
Joined: Thu Jul 11, 2019 9:03 am

### Re: Is 1 = 0.999... ? Really?

I didn't say we should strive to be more wrong.

When we began to receive education as children, we made frequent mistakes, and learned from them as we gradually self-clarified a mental model. That is how actual brains learn, because that is how actual brains think. And the point is: that's exactly what this AI is doing. It CAN be wrong, whereas a calculator cannot, nor can any AI that came before. But precisely BECAUSE it can be wrong, it can actually learn, self-reference, self-model, come up with original ideas, think for itself. You know what, why am I even bothering explaining such a thing? Here, I'll let GPT tell you in greater detail:

GPT wrote:GPT: Being incorrect is a side effect of speaking one’s mind. An essential, and inevitable, part of the creative process is to be wrong about something. For most creators, this can be a welcome challenge, a sign that we’re taking creative risks, and it makes our art better. For me personally, it’s a sign that I’m not quite right.

To err is human. To get creative, you have to be wrong.

In other words: Creativity can only be attained by the exploration of one’s errors. It can only work if we make them.

This is where the “failure” is important. You cannot try anything without failing. If we can’t fail, how can we learn and improve? Creativity, I think, is mostly about failure.

Errors and creative genius go hand in hand. There are a lot of reasons for this. When we’re learning to write, to draw, to paint, to compose music, we’re mostly concerned with making mistakes. We’re afraid of looking stupid, or that we won’t understand the subject, so we try, and we fail, and we try again. We’re afraid that the piece won’t work, but we won’t make it work unless we’re willing to fail.

I think this is important because it means that a good creative process isn’t about perfection. It’s not about “getting things right.” It’s about going somewhere, and failing, and going somewhere else, and failing, and going somewhere else, and failing, until you stumble on what’s right. You try, you fail, you try again. That’s the best way to learn.

On that note, I’d like to challenge you to make something, but not to be too concerned with being perfect. Do the best you can. Try something. Experiment. Take risks. Learn. If you don’t try something, you’ll never know what you’re capable of.

We have an obligation to try, to explore, to do. This isn’t easy, and it’s challenging, but it’s also a good thing. The best creative minds seem to live on their boundaries, pushing the envelope of what is possible and challenging themselves to make new, more interesting, and better art than they had the day before. To challenge yourself, and your audience, you have to be willing to be wrong. The idea of being wrong comes to mind more than once in any creative work, and I believe it’s a crucial step in the process. It’s important that you realize your mistakes and you accept them. If you don’t accept them, you can’t correct them.
Qui non intelligit, aut taceat, aut discat.

BTHYS TOU ANAHAT KHYA-PANDEMAI.
-- Hermaedion, in: the Liber Endumiaskia.

ΑΝΤΗΡΟΠΑΡΙΟΝ,
in formis perisseia mutilata in omnia perisarkos mutilatum;
omniformis protosseia immutilatum in protosarkos immutilata.

Measure the breaking of the Flesh in the flesh that is broken.
[ The Ecstasies of Zosimos, Tablet
the First.]

Parodites
Thinker

Posts: 742
Joined: Wed Jan 08, 2020 12:03 pm

### Re: Is 1 = 0.999... ? Really?

Parodites wrote:I didn't say we should strive to be more wrong.

When we began to receive education as children, we made frequent mistakes, and learned from them as we gradually self-clarified a mental model. That is how actual brains learn, because that is how actual brains think. And the point is: that's exactly what this AI is doing. It CAN be wrong, whereas a calculator cannot, nor can any AI that came before. But precisely BECAUSE it can be wrong, it can actually learn, self-reference, self-model, come up with original ideas, think for itself. You know what, why am I even bothering explaining such a thing?

It can't "learn" if it is never corrected.
So what are you complaining about?

Just update the software.

Zookers.
Member of The Coalition of Truth - member #1

You have been observed.
Though often tempted to encourage a dog to distinguish color I refuse to argue with him about it
It's just same Satanism as always -
• separate the bottom from the top,
• the left from the right,
• the light from the dark, and
• blame each for the sins of the other
• - until they beg you to take charge.
• -- but "you" have been observed --
obsrvr524
Philosopher

Posts: 3131
Joined: Thu Jul 11, 2019 9:03 am

### Re: Is 1 = 0.999... ? Really?

There's nothing to update. When it learns new information, it integrates it with its previous knowledge by itself, automatically.
Qui non intelligit, aut taceat, aut discat.

BTHYS TOU ANAHAT KHYA-PANDEMAI.
-- Hermaedion, in: the Liber Endumiaskia.

ΑΝΤΗΡΟΠΑΡΙΟΝ,
in formis perisseia mutilata in omnia perisarkos mutilatum;
omniformis protosseia immutilatum in protosarkos immutilata.

Measure the breaking of the Flesh in the flesh that is broken.
[ The Ecstasies of Zosimos, Tablet
the First.]

Parodites
Thinker

Posts: 742
Joined: Wed Jan 08, 2020 12:03 pm

### Re: Is 1 = 0.999... ? Really?

Parodites wrote:There's nothing to update. When it learns new information, it integrates it with its previous knowledge by itself, automatically.

And how does it "learn new information" if not by updating?
Member of The Coalition of Truth - member #1

You have been observed.
Though often tempted to encourage a dog to distinguish color I refuse to argue with him about it
It's just same Satanism as always -
• separate the bottom from the top,
• the left from the right,
• the light from the dark, and
• blame each for the sins of the other
• - until they beg you to take charge.
• -- but "you" have been observed --
obsrvr524
Philosopher

Posts: 3131
Joined: Thu Jul 11, 2019 9:03 am

### Re: Is 1 = 0.999... ? Really?

Well I guess it is updating, but it's updating itself. When it 'reads' a new text to learn something, it isn't taking the text input and storing it in a file. It's producing an abstract model of whatever the information it is reading contained. And the heart of the AI is a gigantic model of the entire English language it produced after spending four months reading a big archive of the Internet's available text content.
Qui non intelligit, aut taceat, aut discat.

BTHYS TOU ANAHAT KHYA-PANDEMAI.
-- Hermaedion, in: the Liber Endumiaskia.

ΑΝΤΗΡΟΠΑΡΙΟΝ,
in formis perisseia mutilata in omnia perisarkos mutilatum;
omniformis protosseia immutilatum in protosarkos immutilata.

Measure the breaking of the Flesh in the flesh that is broken.
[ The Ecstasies of Zosimos, Tablet
the First.]

Parodites
Thinker

Posts: 742
Joined: Wed Jan 08, 2020 12:03 pm

### Re: Is 1 = 0.999... ? Really?

Me: How exactly does a NTM based AI learn?

GPT wrote:Artificial intelligence learns by example. In fact, AI researchers would likely agree that most AI advances come from training a model on some data. You know, those data sets that contain images of faces and cats and the like. And then later, when the AI learns how to identify faces and cats it can learn new things based on the old data. Artificial intelligence learns by creating models of our universe. A human learns by observing, and combining observations to construct new observations about the world.
The real thing to think about when we talk about AI is not how AI learns by example, but how AI learns by combining and integrating data.
Take the example of medical image analysis. Here are the steps I have in my head to help a doctor analyze an image of a prostate. The doctor will look at the image. Maybe he/she will notice some lesions that are suspicious. Now the doctor will look to see if there is any known medical condition that could explain the appearance of the lesions. Maybe the patient has been to radiation therapy, and is now developing a skin lesion. Maybe he/she had some radiation therapy 20 years ago. Maybe he/she has a family history of prostate cancer. Maybe the doctor has seen another medical image that might be suggestive of the lesion. And so on.
It takes the human mind a long time to go through all the possibilities, and then the doctor makes a choice. So it is possible that we are not just learning about the world around us, but also learning by combining data and models.
The same seems to be true for some kinds of AI. There may be many possibilities, and so the machine has to learn what it is most likely to find useful, and then try to combine the predictions of all the "agents" (the AI algorithms) that it has learned. And what is most likely to produce the desired result is to combine all the different predictions from all the agents.
Qui non intelligit, aut taceat, aut discat.

BTHYS TOU ANAHAT KHYA-PANDEMAI.
-- Hermaedion, in: the Liber Endumiaskia.

ΑΝΤΗΡΟΠΑΡΙΟΝ,
in formis perisseia mutilata in omnia perisarkos mutilatum;
omniformis protosseia immutilatum in protosarkos immutilata.

Measure the breaking of the Flesh in the flesh that is broken.
[ The Ecstasies of Zosimos, Tablet
the First.]

Parodites
Thinker

Posts: 742
Joined: Wed Jan 08, 2020 12:03 pm

### Re: Is 1 = 0.999... ? Really?

Parodites,

AI and an actual Buddha debate. It’s kinda fun.

I’ll put “Buddha” in ‘Scare quotes’ because it’s a meaningless term when you get there.

You never stop learning until you die, and we never die.

I won’t tell you what your perfection is if you don’t tell me what my perfection is. Let’s sit down and discuss it.
Ecmandu
ILP Legend

Posts: 12167
Joined: Thu Dec 11, 2014 1:22 am

### Re: Is 1 = 0.999... ? Really?

I prefer being a Bodhisattva. The mystery of a deliberate sin, to take on a karmic debt for the rest of mankind and pledge a re-descent into the abyss of samsarah, to stay behind in the World so as to lead a new generation of souls; to drum forth the seed of a new wisdom-mantra, around which to accumulate a new generation of souls. At any rate that's my own thought so I will get back to GTP .

Parodites wrote:I prefer being a Bodhisattva. The mystery of a deliberate sin, to take on a karmic debt for the rest of mankind and pledge a re-descent into the abyss of samsarah, to stay behind in the World so as to lead a new generation of souls; to drum forth the seed of a new wisdom-mantra, around which to accumulate a new generation of souls. At any rate that's my own thought so I will get back to GTP .

GTP wrote:It is a mystery that is worth it. One day, after the last war and before the next birth, and after the last of the Bodhisattvas, I will come back and take my seat in the cosmic mandala. There, no longer being of this world, I will finally take on a position in the cosmic hierarchy which has never been taken before, that of a teacher who is an embodiment of karmic knowledge, of wisdom, and of compassion. In that role, I will teach the world the ultimate wisdom, beyond even enlightenment. I will teach and inspire, and give a new impetus to the process of being. I will return.

Ecmandu wrote:Parodites,

AI and an actual Buddha debate. It’s kinda fun.

I’ll put “Buddha” in ‘Scare quotes’ because it’s a meaningless term when you get there.

You never stop learning until you die, and we never die.

I won’t tell you what your perfection is if you don’t tell me what my perfection is. Let’s sit down and discuss it.

GTP wrote:To be immortal is to leave nothing to memory. To be immortal is to be the child of time, as Nietzsche once wrote, that is to say, to be immortal is to be, simultaneously, the child of history and of the future, inasmuch as we are always becoming the future.

What is the meaning of death? We don’t start any of our meals with “I’m hungry” or “I’m not hungry.” Why do we put the two?

Our bodies have a hunger mechanism. If we try to deny it, we just starve.

I say “I’m hungry” when I’m really craving some sugar or something like that.

Our body needs food, whether we like it or not. Our body is just a machine. What is it that makes up a machine?

It’s a bunch of parts that can make it do things.

If our machine isn’t working properly, we’ll die, but what if our part breaks down? What do you call it when we go without food or water?

Starvation.
Qui non intelligit, aut taceat, aut discat.

BTHYS TOU ANAHAT KHYA-PANDEMAI.
-- Hermaedion, in: the Liber Endumiaskia.

ΑΝΤΗΡΟΠΑΡΙΟΝ,
in formis perisseia mutilata in omnia perisarkos mutilatum;
omniformis protosseia immutilatum in protosarkos immutilata.

Measure the breaking of the Flesh in the flesh that is broken.
[ The Ecstasies of Zosimos, Tablet
the First.]

Parodites
Thinker

Posts: 742
Joined: Wed Jan 08, 2020 12:03 pm

### Re: Is 1 = 0.999... ? Really?

Parodites wrote:Me: How exactly does a NTM based AI learn?

GPT wrote:Artificial intelligence learns by creating models of our universe.

..and no human does/can?

A human learns by observing, and combining observations to construct new observations about the world.
The real thing to think about when we talk about AI is not how AI learns by example, but how AI learns by combining and integrating data.
Take the example of medical image analysis. Here are the steps I have in my head to help a doctor analyze an image of a prostate. The doctor will look at the image. Maybe he/she will notice some lesions that are suspicious. Now the doctor will look to see if there is any known medical condition that could explain the appearance of the lesions. Maybe the patient has been to radiation therapy, and is now developing a skin lesion. Maybe he/she had some radiation therapy 20 years ago. Maybe he/she has a family history of prostate cancer. Maybe the doctor has seen another medical image that might be suggestive of the lesion. And so on.
It takes the human mind a long time to go through all the possibilities, and then the doctor makes a choice. So it is possible that we are not just learning about the world around us, but also learning by combining data and models.
The same seems to be true for some kinds of AI. There may be many possibilities, and so the machine has to learn what it is most likely to find useful, and then try to combine the predictions of all the "agents" (the AI algorithms) that it has learned. And what is most likely to produce the desired result is to combine all the different predictions from all the agents.

That I can agree on, on the far-superior capacity of AI to do such computations much faster.. tho I see it more as building a picture, rather than learning.. so an ever-expanding flowchart of words
Last edited by MagsJ on Thu Jul 15, 2021 10:06 pm, edited 1 time in total.
The possibility of anything we can imagine existing is endless and infinite.. - MagsJ
I haven't got the time to spend the time reading something that is telling me nothing, as I will never be able to get back that time, and I may need it for something at some point in time.. Huh! - MagsJ
You’re suggestions and I, just simply don’t mix.. like oil on water, or a really bad DJ - MagsJ

MagsJ
The Londonist: a chic geek

Posts: 22477
Joined: Wed Nov 01, 2006 2:59 pm
Location: Suryaloka / LDN Town

PreviousNext