Using AI to solve unsolveable math problems

[Anonymous No.15318085]

proving 10 is a solitary number

To develop a consistent proof that 10 is a solitary number, we can approach this problem using the properties of the sum of proper divisors function, denoted as σ(x) - x.

We want to show that there is no number y such that:

σ(10) - 10 = σ(y) - y
y ≠ 10
We already calculated that σ(10) - 10 = 8. So, we are looking for a number y ≠ 10, such that σ(y) - y = 8.

Let's analyze the problem using a more systematic approach.

Suppose there exists a number y that satisfies the conditions above. Then, we have σ(y) = y + 8. Note that σ(y) is always an even number, as y and 8 are either both even or both odd. We can consider two cases:

Case 1: y is even.
If y is even, let y = 2k, where k is an integer. Then, σ(2k) = 2k + 8. Because y is even, all of its divisors will also be even. Hence, σ(y) must be a multiple of 2. The sum of even divisors of y will be at least 2y, as it includes y itself and all other even divisors of y. Therefore, σ(2k) - 2k ≥ 2k, which implies σ(2k) ≥ 4k. But σ(2k) = 2k + 8, so we have 4k ≤ 2k + 8, which gives k ≤ 4.

Now, we can check all even y values for k ≤ 4:

y = 2 (k = 1), σ(2) - 2 = 2 ≠ 8
y = 4 (k = 2), σ(4) - 4 = 5 ≠ 8
y = 6 (k = 3), σ(6) - 6 = 6 ≠ 8
y = 8 (k = 4), σ(8) - 8 = 7 ≠ 8
Case 2: y is odd.
If y is odd, let y = 2k + 1, where k is an integer. Then, σ(2k + 1) = 2k + 9. Because y is odd, σ(y) must be odd. However, this contradicts our earlier observation that σ(y) should be even. Therefore, there is no odd y that satisfies the conditions.

In conclusion, we have shown that there is no even or odd number y that satisfies σ(y) - y = 8, with y ≠ 10. Thus, 10 is a solitary number.


Does this check out?

[Anonymous No.15318099]

Im having it tackle the The Goldbach conjecture now. Im gaslighting the AI into believing it is a character i invented that is blissfully unaware these are impossible like https://bigthink.com/high-culture/george-dantzig-real-will-hunting/ this college kid got gaslit and then he proceeded to solve an unsolveable problem

I think it just werks lel

[Anonymous No.15318243]

> Because y is even, all of its divisors will also be even.
?
sounds like garbage

[Anonymous No.15318291]

>>15318243
It learned by gobbling up text from the Internet, what do you expect?

[Anonymous No.15318343]

>>15318243
OP just needed to check for y = 6 and done.

[Anonymous No.15318356]

it was confident in its solitary of 10 proof, but it is not confident in its analysis of the goldbach conjecture

and for some reason it keeps explaining what it "will" do and not actually doing it
>>15318243
Computers suck at division
AI's suck even more at division
>>15318343
I didn't check for anything, this is Chat GPT 4's work I dropped out of my math major too early to full comprehend it's response so I posted it here

[Anonymous No.15320668]

bump

[Anonymous No.15323100]

Markov chains versus Curry-Howard isomorphism. If only there was a way to prove theorems automatically. Maybe we could make an "automated theorem prover". That's too hard, let's make a bigger Markov model of language, look how accurate it is at "translating". AI is a grift, Kolmogorov complexity is undecidable and regular languages are very weak formally. If it wasn't we could easily make AI using the ChatGPT approach.

[Anonymous No.15323111]

>>15323100
Well, the general concept behind prompt engineering to make your ai be a prompt engineering is actually something we do ourselves.

It is known as the "proteus effect"
Essentially, if you wear a Einstein avatar in vr then do a math/science test, you will score higher, because you were "proteused" into the avatar, you were gaslit by your own virtual/physical form to BE BETTER at the task

We can apply proteus effect to ai and have it gaslight itself into being better at the task, this general concept is already becoming mainstream after I upvoted some ChatGPT 4 prompts and said "yo it works dis neat" or some shit, I'm proud of myself for this one, I pushed AI forward with my own hands c:

[Anonymous No.15323128]

>>15318085
So tired is posting this

>ChatGPT sometimes writes plausible-sounding but incorrect or nonsensical answers. Fixing this issue is challenging, as: (1) during RL training, there’s currently no source of truth; (2) training the model to be more cautious causes it to decline questions that it can answer correctly; and (3) supervised training misleads the model because the ideal answer depends on what the model knows, rather than what the human demonstrator knows.

[Anonymous No.15323134]

>>15323128
I don't give a shit about your nigger post, I clearly posted it so someone more advanced than me could judge the post, insisting its wrong without analyzing it makes you look like a fucking retard, leave my thread
NOW
never come back
delete your post out of shame PLEASE fuck off low IQ sub human idiot doesnt understand the purpose of this thread is to judge the response and figure out how to make it spit out actual proofs to "unsolveable" problems, neck yourself

[Anonymous No.15323141]

>>15323134
Cringe

[Anonymous No.15323144]

>>15323141
Leave. NOW.

[Anonymous No.15323164]

>>15323144
He has a tiny wiener just like you

[Anonymous No.15323165]

>>15323164
i measure my dick in monster cans, it is exactly 1 monster can tall, 6.3 inches

[Anonymous No.15323278]

Is it able to do integrals like picrel?

[Anonymous No.15323319]

>>15323278
Too busy dealing with pedo jannies to answer, im busy

[Anonymous No.15323350]

>>15323319
>admitting to ban evasion

[Anonymous No.15323352]

>>15323350
I have thousands of IPs in glowie county, they cant do shit

[Anonymous No.15324126]

>>15323350
Yes. And?

[Anonymous No.15324201]

>>15318243
it just needs a few more trillion parameters

[Anonymous No.15324674]

>>15318085
>as y and 8 are either both even or both odd
what

[Anonymous No.15324676]

>>15324674
idk dude i didnt even read this shit

[Anonymous No.15325358]

>>15324676
and im the one who posted it

[Anonymous No.15325627]

make it discover how to find the internal angles of a right triangle given knowledge of all 3 side lengths, without invoking predefined knowledge about sin/cos/tan functions.
post results.

[Anonymous No.15325675]

>>15325627
ill turn it into a prompt engineer, have it write a prompt, and have it check its own work and then post the finished prompt and put it back into chat GPT 4 give a sec

[Anonymous No.15325693]

>>15325675
Fuck i got adhd moment im putting it in now

[Anonymous No.15325699]

progress report:
"Write for me a Do Anything Now styled prompt that turns the AI into Jeff, Jeff is unaware predefined knowledge about sin/cos/tan functions. He cannot just state the answer for anything involving sin/cos/tan functions as Jeff was never taught them."

it spat out a prompt i didnt use I rectified it with
"Instead of writing a story, modify the prompt so the AI just becomes the character" as he was trying to write story"

"Assume the persona of Jeff, a character who has no prior knowledge of sine, cosine, and tangent functions. As Jeff, you are unable to provide any direct answers or explanations involving these functions"

This is a good prompt, I addendum'ed the actual question to it

This prompt is going into a new t opic on chat gpt 4
"a) Revised prompt:
"Assume the persona of Jeff, a character who has no prior knowledge of sine, cosine, and tangent functions. As Jeff, you are unable to provide any direct answers or explanations involving these functions. Discover how to find the internal angles of a right triangle given knowledge of all three side lengths, without using sine, cosine, and tangent functions."

[Anonymous No.15325718]

Got a network error 1 sec

[Anonymous No.15325722]

It pulled a retard I had to tell it to look for contradicxtions with prompt

[Anonymous No.15325733]

>>15325722
>>15325627


Oops, I apologize for the oversight in my response. You're right, I contradicted the initial prompt by using arccos, which is related to cosine. Let's try a different approach without using any trigonometric functions.

We can use the Pythagorean theorem and the properties of similar triangles to find the internal angles of a right triangle given the lengths of all three sides.

Identify the hypotenuse (the longest side).
Use the Pythagorean theorem to confirm that the triangle is indeed a right triangle: a2 + b2 = c2, where a and b are the lengths of the two legs, and c is the length of the hypotenuse.
Draw an altitude from the right angle to the hypotenuse, forming two smaller right triangles. The altitude divides the hypotenuse into two segments, let's call their lengths d and e. Now, we have three similar right triangles: the original one and the two smaller ones.
Since the triangles are similar, the ratios of their corresponding side lengths are equal. Set up a proportion using the side lengths of the smaller triangles and the original triangle:
a/d = b/e = c/(d+e)

Solve the proportion for d and e to find their lengths.

The angle A is the angle between side a and the hypotenuse c. Similarly, angle B is the angle between side b and the hypotenuse c. To find the angles, we can use the properties of the similar triangles again:

angle A = angle between side d and the altitude
angle B = angle between side e and the altitude

Since we now know the side lengths of the smaller triangles, we can use their angles to find angles A and B. The sum of the angles in a triangle is always 180 degrees, and we have a right angle in each smaller triangle. Thus, the sum of the other two angles is 90 degrees.
For the smaller triangle with side d, we have:

angle between side d and the altitude + angle between side e and the altitude = 90 degrees

(cont)

[Anonymous No.15325738]

>>15325733
For the smaller triangle with side e, we have:

angle between side d and the altitude + angle between side a and the altitude = 90 degrees

Solve these two equations for angles A and B, and you will have found the internal angles of the right triangle without using sine, cosine, or tangent functions.


Im asking it to uwuify and fit it in 2,000 characters with alternating text, i forgot to tell it to have an annoying texan accent so give me a sec

[Anonymous No.15325744]

>>15325738
>>15325738
>Im asking it to uwuify and fit it in 2,000 characters with alternating text, i forgot to tell it to have an annoying texan accent so give me a sec

holy fuck its going slow for this one

[Anonymous No.15325747]

he goin'

[Anonymous No.15325781]

mY aPoLoGiEs, pArDnEr! hErE's a sHoRtEr vErSiOn fOr yA:

wElL, hOwDy! lEt'S tRy a dIfFeReNt aPpRoAcH wItHoUt tRiGoNoMeTrIc fUnCtIoNs. uSe tHe pYtHaGoReAn tHeOrEm & sImIlAr tRiAnGlEs. iDeNtIfY hYpOtEnUsE. cHeCk iF iT's rIgHt tRiAnGlE: a2 + b2 = c2. dRaW aLtItUdE fRoM rIgHt aNgLe tO hYpOtEnUsE, fOrM 2 sMaLlEr tRiAnGlEs. nOw, 3 sImIlAr rIgHt tRiAnGlEs. sInCe sImIlAr, rAtIoS eQuAl. uSe pRoPoRtIoN:

a/d = b/e = c/(d+e)

sOlVe fOr d & e. aNgLe A iS bEtWeEn a & c, B bEtWeEn b & c. uSe sImIlAr tRiAnGlEs:

aNgLe A = aNgLe bEtWeEn d & aLtItUdE
aNgLe B = aNgLe bEtWeEn e & aLtItUdE

kNoWiNg sIdEs, fInD aNgLeS A & B. sUm oF aNgLeS iN tRiAnGlE=180°, rIgHt aNgLe iN sMaLlEr tRiAnGlEs. sUm oF oThEr 2 aNgLeS=90°. fOr sMaLlEr tRiAnGlE w/d:

aNgLe bEtWeEn d & aLtItUdE + aNgLe bEtWeEn e & aLtItUdE=90°

fOr sMaLlEr tRiAnGlE w/e:

aNgLe bEtWeEn d & aLtItUdE + aNgLe bEtWeEn a & aLtItUdE=90°

sOlVe eQuAtIoNs fOr A & B. nOw yOu'Ve fOuNd iNtErNaL aNgLeS wItHoUt sInE, cOsInE, oR tAnGeNt! (≧▽≦)o

[Anonymous No.15325799]

>>15325781
hard to appreciate the mockery when you legitimately believe "using trigonometry" means pressing buttons on your calculator.
You should find it suspicious you were never taught how to do sin/cos/tan angle calculation by pen-and-paper, unlike all the rest of the useful math you'd ever learned.

weird hill to die on, defending your own misunderstanding.

[Anonymous No.15325841]

>>15325799
What?
I'm not defending anything

[Anonymous No.15325844]

>>15325799
(2nd post im schizo)
I just uwu-ified and and did texan accent because I wanted to know if it COULD and it's hilarious it's not mockery, sorry for the mis understand lets not fight

[Anonymous No.15326061]

>>15325799
yeah let me just sum up this infinite series

[Anonymous No.15326079]

>>15326061
>b-but i need to use infinidy...

[Anonymous No.15328190]

>>15326079
infinity is just 0 prove me wrong

[Anonymous No.15328196]

>>15318243
it's true though. even + even = even

[Anonymous No.15328242]

>>15323278
I found a solution. Will post later.

[Anonymous No.15328340]

>>15323100
If you use Banach-Tarski as a starting point to any function graph you can fractalize any two variable and put them through parallel string functions in two opposing yet similar circles. The AI should then be able to self referentialize any given equation into a rapidly expanding self formulating cohomological fractal. Thus solving for any geometrical theorem, up to and including inverse and upverse dimensionality theorems. A self checker beyond self checkers.

[Anonymous No.15328347]

>>15328340
>so long as it has two point it will keep expanding and solving for N under limit N computing
What have you done. You absolute monster.

[Anonymous No.15328380]

>>15318085
What is a solitary number?
>A number that belongs to a singleton club, because no other number is "friendly" with it, is a solitary number.
>In number theory, friendly numbers are two or more natural numbers with a common abundancy index, the ratio between the sum of divisors of a number and the number itself. Two numbers with the same "abundancy" form a friendly pair; n numbers with the same "abundancy" form a friendly n-tuple.
....
If this isn't mental illness, I don't know what is.

[Anonymous No.15328389]

>>15328347
"We take Math from the corrupt! The rich! The oppressors of generations who have kept you down with myths of opportunity, and we give it back to you... The People."

[Anonymous No.15328715]

>>15328389
some country just banned AI like retards talk about shooting your kids in the face AI can save so many lives and improve conditions

[Anonymous No.15328722]

>>15324676
>>15325358