Don't forget to check out the accompanying FREE Maple Learn worksheet: learn.maplesoft.com/doc/z4tp3rbsw6

ChatGPT is very good at convincing people that it knows what it's talking about even if it's talking complete nonsense, and I think it tricked Tom in some of the "show that" questions 😂

I would recommend trying GPT 4! It's logical reasoning skills are leagues better than the version you are currently using

It's interesting seeing how far ChatGPT is coming as far as utilization across many contexts and platforms. Cheers for the lengthy and detailed showcase man!

It normally messes up with basic maths but has good logic with gpt4 with its Mathematica plugin I found it was able to score around a 2-1 and even a 1st in some of the old modules I took in my physics degree as I had some old pass papers and thought it would be a fun little test.

"^" means exclusive-OR (XOR). I saw sometimes ChatGPT evaluates "^" as power and sometimes as XOR. It's better if you do something like pow(x, y). However latex identify "^" means power.

Interesting experiment. Would very much like to see this done again with latest version 4 and maths plug in. (I studied maths at Oxford as post grad and am astounded at how rusty I am when I watch your vids Tom).

Your video of Gabriel trumpet was amazing. Still my favorite so far.

An old manager of mine was Tom Crawford. He was from the Pittsburgh area of PA.

It's actually really good for helping you with some maths problems

You should try this once GPT-4 becomes available! It will have a vast amounts in improvements. Also you’ll be able to give the program pictures/screenshots of the questions so you don’t have to type it all in😆

I just ran through all the multiple choice with GPT4 and the Wolfram Plugin and it got them all right the first time.

I think for 1E it worked out the probability 3 ways and added them together, that's why it got 45/64 instead of 15/64 and did the summing.

Love your videos Sir Crawford. ❤Love from Spain.

Really interesting experiment! Some of its mistakes are fascinating, like at 6:33 it correctly identifies the substitution that turns it into a quadratic equation, but ends up switching what y and y^2 should be; I wonder what a model trained specifically for math could do. What are your thoughts on how ChatGPT or automated theorem provers like Lean could transform research-level math in the next few decades?

13:30 I'm not really a mathematician, but rather an aspiring applied linguist but I will give this a shot. When trying to set up the simultaneous equations, it got the second equation wrong (the x and y are meant to swap around) What it wrote (12:33): x + 3y = 10 y + 2x = 8 (this leads to the solutions x = 4/5, y = 12/5 where neither are integers and it does not satisfy the third condition, x + y = 6 since there are six vectors) What it should have written down: x + 3y = 10 x + 2y = 8 The second mistake it made was identifying '3 possible solutions' as 'actual solutions' and was trying its best to use the binomial formula with 'all 3 solutions'. This is a system of linear equations, there should only be 1 solution. It didn't bother to reject some of the solutions. (13:01) It deduced from its incorrect working that 3y and x need to be even. It chose 'correct y values' that satisfy this condition, but sometimes I have no idea how it got those x-values. It got (4,0) as a solution by using the condition that y needs to be even, so y = 0, 2, 4 and substituting y = 0 into the second equation gives x = 4. I do not know what it did with y = 2, 4 and why it only considered those 3 y values. (12:53) Later on, it did interpret the binomial coefficient for P(X=4, Y = 0) as 6 choose 4 [which does end up being the right one to choose as this leads to 15/64, the correct soln]. However, pulling 6 choose 4 like that from seeing 6 vectors and x = 4 sends a few red flags as in this case y should equal 2 for x + y = 6 (11:10) However, it treated the other two as valid solutions and tried to sum all 3 which leads to another handwavy 6 choose 2 and 6 choose 4 being calculated with both being equal to each other due to the symmetry of Pascal's triangle. (11:14) This led to ChatGPT's answer being three times too big. (11:16) It's pretty funny looking at its working. In a way, it sort of got it right with incorrect logic. It tried to insert 6 choose 4 or 6 choose 2 somewhere out of its incorrect working. It tried its best to do sensible things, but the logic was not quite there. In summary, it made a mistake by writing the second linear equation incorrectly. However, that was not its only mistake. It did not use correct logic based on the incorrect simultaneous equations to get (6 choose 4) or (6 choose 2) even though those were the correct binomial coefficients to use. Lastly, it failed to identify that simultaneous linear equations must have at most 1 solution.

I did the first part of the test (multiple choice) with GPT4 twice. Once mentioning the solutions, once not mentioning them. GPT4 performed significantly worse when not knowing the possible answers. Which makes sense, a student would be the same way. With answers given, it had only 2 questions wrong. Without answers given, it failed 5. Edit: Also, GPT has a character limit to its responses. So when it just stops half way through an answer, you can say "go on" and it will continue where it left off.

Thanks Tom. Love your content & this was lots of fun. Made me think for a moment that the Turing Test should incorporate some of these OxfordUni math questions & then I realised that most humans would score far worse. So far I’ve found gpt-4 a step up from chatgpt but math still seems a (relative) soft spot in the AI

My dream is to get a chance of admission in Oxford, i am still trying my best to succeed...Huge fan, i love your explaining...keep up the good work🎉

ChatGPT is able to represent equations with the same appearance as those presented on paper or by hand. On the other hand, we must absolutely specify that we want this kind of writing and not writing on a keyboard that is very complicated to read. Just make a pasted collar of the following text: -Now, if you need to write a mathematical expression, use katex notation and follow these rules: 1. If it is a block equation, display it in a single P element and wrap it in dollar signs double like this: $$e=mc^{2}$$ 2. If it is an inline equation, use katex's double backslash and parenthesis notation, like this: \(e^{i \pi}-1=0\).- Another thing to keep in mind is that ChatGPT4 is vastly better than ChatGPT3.5. We keep in mind that version 3.5 is simply a demo version and that the vast majority of errors are fixed in version 4. Besides, I myself subscribe to version 4 and I don't want to know anything more from version 3.5! Otherwise, great video! Very interesting!

Pretty interesting. I sometimes use it for VB programming and it writes really good code. You need to be as detailed as possible and it always gives me correct results. I'm very impressed by it. I have been entering some of my old code and it is simplifying it for me, saving me a great deal of time.

once you find that the central angle is 30, then the area is 1/2 a * b * sine 30, where a and b are indeed radii. 1/2* 1* 1* 1/2 * 12 = 3. This is ninth-grade math. GPT's error was using 30 degrees (and using a special triangle) instead of 15 degrees for the half triangle. That is why it got the height wrong.

So interesting loved the video

So I plugged some of these questions (around 15) into gpt4 and it got all of them correct

Chat GPT is an AI language model and is trained with words and phrases not really mathematical equations, so if u ask it a question, it seasrches it whole database for an answer, it doesnt actually calculate the equation itsself, and if it an equation and it doesnt find it in its database, it will just say it cant solve it as its an AI language model

I used this to help a friend answer medical quiz questions such as suggesting treatments based symptoms. It was right about 90% of the time.

Particularly in the multiple choice section, it would have been interesting to prompt the model in the identical way that it's asked in the question for humans alongside giving the options, and giving the exact representation of the integral using latex notation rather than using English to describe it. My experience is that it varies wildly in GPT-3.5 but significantly more robust in GPT-4!

On the problem at 46:40, it is true that b and d are zero, and that is the requirement for a polynomial being an even function. It's just crazy it didn't explicitly show it by expanding f(x) using that prior form.

For question 2, it seems as if the error occurs at 5:05. It says substituting y = a^(3/2) But in doing so, it turn the a^3 into y. which isn't right. Don't know it substitutes instead of going straight to factorising. As that's pretty easy, as a^3/2 and a^3 very clearly have a common power, and 3/2+3/2 = 3.....

The same thing happened with the Russian Unified State Examination (ЕГЭ). ChatGPT wasn't able to compete with that test, especially with the second part of the exam where detailed answers are required for complex trigonometry equation, complex logarithmic inequality, economical problem (credits), stereometry, geometry, equation with x and an unknown parameter and the last one is problem from number theory.

Wow I spent my Christmas afternoon watching. I found this video riveting. 😂

15:52 to be fair, GPT said "(...) also passes through the point (2,0) for two values of a, namely (...)". You could interpret it as "It passes for another value that I divided before, but also through these two" :D

The first one: ChatGPT simply took the solution for the hexagon (where you really get equilateral triangles) and simply replaces the factor 6 by the factor 12. Which is nice, 3sqrt(3) is definitely larger than pi. In fact if we look at the options all but b) and e) are larger than pi. Basically ChatGPT is saying: I know a solution to this similar problem, and will solve it by simply changing each occurance of the number 6 to 12. Also for E) (the combinatorics one): ChatGPT used the equations x + 3y = 10 and y + 2x = 8, should have been x+3y = 10 and x+2y = 8, which gives the correct solution that y = 2 and x = 4, which then gives the correct answer 1/2⁶ (6 2) = 15/64. G) Is one heck of a question. It can be spelled by including sin(0)^2 (which is 0), recognizing that this is the same as summing over the cosine squares (just in reverse direction), so 2A = 1 + 1 + ... + 1 = 91. Thus this could be generalized to: Let µ be a measure on [0, pi/2] that is symmetric around pi/4 (so µ(A) = µ(pi/2 - A)). Then integral_[0, pi/2] sin²(x) dµ(x) = 1/2 µ([0, pi/2])

Did I just watch an hour and twenty minutes of a guy making Chat GPT do maths instead of revising for my exams? Yes. Yes I did. Do I regret it? Not one bit.

One very big thing I think you might've missed out on experiencing is correcting the mistakes. For example making a follow up query such as "i'm not convinced on your algebra after step ... ". Or "can you explain why you did ... on step 3". The follow up query's are what have helped me learn a lot while cheating on my homework since it makes you have to deeply understand the question to know what part of it is even the answer.

Hi Have you ever considered doing a podcast in which you discuss the latest developments in maths

I used it for programming and it’s sooo helpful. I don’t know if I needed 10x more time or more for the same task without it or if I would even be able to do it.

10:16 of course it got this right, cause he helped me to solve the exact same question in my homework

im curious to see you try the singaporean further maths exam and see how that compares to the one in the uk

Absolutely fascinating exercise (verification?). A similar exercise has been done internally @ MSFT Research. I wonder how we could define a comprehensive public review/expert feedback of Chatgpt's math "ability" using the latest version of Chatgpt. The Chatgpt version here does not include all known corpora of maths knowledge(?).

other people have already pointed out that GPT 4 is a large logic improvement over Chat GPT, i think its also worth pointing out that this Model doesnt "think" or "knows" anything. its just a lot of data from various different sources fed in to a really fancy algorithm and its pretty good at finding patterns and figuring out the logic but the more detailed results you ask from it the worse it will get because and this is true especially in math even more then other topics, every minor error adds up together and can end up in a very wrong result. so it will do a lot better if you formulate it in a way or ask for something that allows to ignore some of the finer details or give it questions that dont require such a fine detail to be able to answer them. as a person in the comments already pointed out, it also does a lot better if the possible options are provided to it because instead of finding ANY solution it "thinks" to be valid, it will then instead go through each option and answer which one it is the most confident to be the right answer, which will help gloss over of some of the errors it does because it will just pick whats the closest to the answer it gets. unless it mixes up the answers as well which i think it did in one of the questions and then used the number from one answer but the value that the number represents of a different answer. the answer value was correct but worth pointing out that even in a simple list of 5 options to pick it sometimes confuses which number in the list has which option. Ai "thinks" very different to how humans do because computers have always processed information different then humans and that means you have to also formulate the question for someone who thinks like this Ai model and not like you would for a human to get results comparable to humans. this wont get rid fully of all the logic errors it made but that combined with using GPT 4 would probably have elliminated most mistakes it did.

I think it got question 1C correct for the wrong reason. It came to the conclusion that a = p - ln2 and b = q - ln2 and therefore that p - a = q - b (since they are both ln2). In actual fact a = p - 1 and b = q - 1 and hence p - a = q - b but because they are both equal to 1 not ln2.

From David ; chat GPT version 6 or 7 or 8 will 100 percent pass the exams when it gain access to the data ( include concept information : not yet included here in the earlier beta version of chat GPT ). The future test will need to be construct to ( find the capacity of “ human creativity” ability levels ) as oppose to ( data learning of past input ) from ( previous human discoveries )

It's fascinating how often it gets tripped up by a simple algebraic mistake. Like on this one 13:27, it's mixed up the x and the y, since it should be x + 3y = 10 and x + 2y = 8, since y is how often (3,2) is chosen. From there it could solve the equations. Also, later on for the same question, it classed x = -1 and x = -6 as valid solutions, but if x is how often (1,1) is chosen then x can't be negative at any point. Nice to know ChatGPT won't be taking over any time soon 😂

Remember: when working with these kind of AIs: always stay vigilant. Collect its answers, doubt the answers and "at least" let it source its answers against itself. For example: I was looking for measurement units where two use the same abbreviation. It said there are none. This made me sceptical as there are two kind of tonnes, that aren't standardized. So I straight up asked it wether long tonnes and short tonnes use the same abbreviation. It told me no - quite confident even, it used the word "nope" - reasoning short tonnes use "t" and long tonnes use "T". I asked it who decided that and it replied that international organisations like SI is doing that. Since I know that tonnes isn't a SI unit (or base unit at least) I pressed it again who decided that this ton is t and that ton is T and it then admitted there is no standardization for this. Yes, it is a great tool to skim a lot of information quickly. But sadly, it is just skimming and people need to still input actual work in double checking the responses.

love this one

I gave chat gpt a vatiation of one of thr questions from the 2022 mat (i believe question 5) and it came up with an incorrect (albeit very interesting) solution so im curious to see how it handles the rest of the mat paper

I am German and maybe I have not really understood your evaluation and your opinion about the efficiency of ChatGPT. I was astonished ChatGBT was able to solve some of these math problems.

I think that you should have given ChatGPT the options too,because then,if it got an answer that is not there in the options,it would have atleast made a guess or try to correct itself. Then it would have definitely gotten more answers correct.

On question 1, you know the area is less than pi since it's inside an unit circle so b) and e) are the only possible answers.

First time I used ChatGPT for math, I wanted to know battery time with a constant rate of expenditure. It started out good, but I was pretty disappointed when ChatGPT multiplied its total runtime in hours (which it calculated) with the amount of weeks in 3 months

Tom - i have absolutely no commercial interest, but I strongly suggest re-running this test with the Wolfram Alpha plug-in for GPT4. WA does the computation. GpT4 just translates from English to Wolfram langauge and back again. So it should massively outperform GPT3.5. All good wishes, Ian

It is really frustrating that you didnt give it all the answers... i dont think it is fair considering a student would have access to them.

ChatGPT is like a good politician: It's making sure you thinks it knows what it's talking about even though that is complete nonsense.

Some slight critique: I think it would have been more representative if for every multiple choice question all answers would have been provided to GPT. I reckon that most applicants are using those answers to cross check wether their answer is correct or if they thought the wrong direction Cheers

With the very first question, if you type in the assumption provided in the question, you'll get the right answer. For example, if you type: "Assume the area of a single triangle is 0.25. A regular dodecagon is a 12-sided polygon with all sides the same length and all internal angles equal. If I contrusct a regular dodecagon by connecting 12 equally-spaced points of a circle of radius 1, then the area of the polygon is?"

i feel like its because thats the gpt-3 model, but gpt-4 is far more better and well trained + now there are plugins available to make things more easier and accurate so maybe we need a part 2 of this video sir😜, amazing video as always!!!

I'd want to see how GPT-4 would do.

10 years later, chatGPT is going to fight back, getting every single question right and breaking the test

If it's multiple choice at least give it the multiple choice options each time, with its true/false verification it would be interesting to see if any of the zero mark questions actually gave you a positive response with the extra info

You can ask Chat GPT to put the answer into latex too. It can talk but it makes lots of basic arithmetic mistakes.

Wirh multiple choice questions - chatGPT should get every choice to check for for better results so if it messes up its way to the answer it can recheck

I wonder if there would be any difference if you also provide the answer? An MCQ is different from a SAQ afterall

often if the result is wrong i just type "are you sure about your results?" and if there is an actual mistake in the calculation it will write you a second attempt on the question

I tried the first question in ChatGPT4, and it got the right answer (3) 3. --- tsuchan1: Ok. Let's d this step by step to avoid mistakes. This is a multiple-choice question and one answer is correct. A) A regular dodecagon isa 12-sided polygon with all sides in the same length and all internal angles equal. If I construct a regular dodecagon by connecting 12 equally-spaced points on a circle of radius 1, then the area of this polygon is: a) 6+(3 Sqrt(3)) b) 2(sqrt(2)) c) 3(sqrt(2)) d) 3(sqrt(3)) e) 3. Which answer is correct? ChatGPT: To find the area of a regular polygon, you can use the following formula: Area = 1/2 * n * r^2 * sin(2π/n) Where: n is the number of sides (for a dodecagon, n=12), r is the radius of the circumcircle (in this case, r=1), and π is a constant (approximately 3.14159). Substituting these values into the formula, we have: Area = 1/2 * 12 * 1^2 * sin(2π/12) = 6 * sin(π/6) Since sin(π/6) = 1/2, the area of the dodecagon is: Area = 6 * 1/2 = 3. So, the correct answer is (e) 3.

I'm curious how ChatGPT would have done if you had listed the choices for each question in the multiple choice section.

The fact chat gpt is so good genuinely terrifies me. I'm so scared of ai's potential, and no not in the way "it'll grow so smart that it'll control humans like the matrix" no, more like in the way, it has the ability to take over many jobs and I worry abt a lack of careers in the future...

I would love to re-do it with giving the multiple choice answers to the AI

This means very little if you are using ChatGPT rather than GPT-4. Surely any student will be using GPT-4 or better.

A better question Doc, is to ask why anyone would want to program any AI to pass things like the Oxford Math(s) Admissions Test in the first place and whether that is an ethical thing to do(?) 😛

If you provide the multiple choice answers, it will check against them. Which is what a human would do. So I think it's only fair to include them in future episodes. Note that the one time you provided all multiple choice possibilities, it got the answer right.

Shame I missed the premiere on this!!! 🤖

As others have said, chatGPT 4 would likely do better and to be fair, I think you should have included the possible answers when asking the question in the same way a human has access to the possibilities.

I don't think you needed to edit the questions nearly as much as you did. I copied the first question into chatGPT exactly as written with the answer options and it came up with the same reasoning and the same wrong answer but stated more clearly: "Therefore, the correct answer is (d) 3√3."

Only just started watching the video but I it interesting that for the first question, 3 of the 5 answers are greater than π.

For the first one the answer is close to pi, so 3.

Chat GPT often got basic algebra questions wrong. I stopped using it past calculus.

I noticed that chatgpt is good at most things except maths

yes

What an eccentric individual

I think that Ɓ / sum of 6²=π²/4*4=f(10)

Try it again at some stage now that it has access to the Wolfram Alpha plugin.

Item e one must ignore the cases where x

It's not going to pass a maths test unless its lucky. It doesn't get rules based logic to the exent that's required.

TOM'S GREAT😊

Some times it present logically flawed information, I ask it to show me section 55 of contract act, it said there is no section 55 in contract act as there are only 75 section in that act.😅

I'm obviously no expert, but I doubt "exceptionally entertaining" is the standard for the Oxford Admissions test :)

Should use GPT4, this is the very basic version and lags in certain areas.

actually for question j chatGPT got it right, it got answer d, which implies also that all of those equalities are true, bot answer a,b,c were wrong becuase of the if and only if form, which doesnt hold since all of the 3 conditions have to be true at the same time

Scarily enough GPT-4 Aces those first two questions especially when given the full question (including the choices). I didn't have the wherewithal to type any more in but I guess it has since figured out math to a higher degree of fidelity

It may do better to use it as a tool, such that to divide each query into smaller questions. But obviously that’s not the title of the video.

For the first question, the dodecagon necessarily has to be circumscribed by the circle whose area is 3. Meaning the dodaceagon must have an area less than the circle. The only option being B. You don't even have to do math for that question unless my logic is wrong somehow?

Took the test myself, and got a score of 24-12-12-15-10 for Q1 to Q5. Most of the errors were mistakes like accidentally using the wrong inequality, messing up the algebra, or skipping an important detail. But overall it was pretty fun I haven't watched the whole video yet but I'm interested to see how chatGPT solves these problems, and what strategies it might use

absolutely:)

Just wondering if correcting for real apliccants is so "sweet"( so as to say is much like, no answer exactly the same as the solution gets a zero mark)

Large language models are only as good as the prompt they are given.

Hello, I really enjoyed your video. I'm a mature student that failed maths as a teenager and I want to retake it. Are there any websites you recommend? I love Khan Academy, but I worry as it's tailored towards the American system?

Laws of Potential Energy 1 Vacuum Once you take the contents out of matter the potential of that matter rises and simply converts to kinetic energy. Reasoning states that vacuums want to collapse upon itself, but this observation can only be explained by gravity. Matter must be the only thing that can attract or repel matter. Furthermore, any surmountable equivalently rational of matter can attract that matter and any matter less than itself. Presumably walls of a vacuum must be attracting each other. ______________________________________________________________________ 2 Matter in a Vacuum Matter surrounded by a vacuum, that matter's potential energy will rise. Reasoning states that if we have nothing around us we'd move through space easier potentially. ______________________________________________________________________ 3 The Complexity of Matter The combination of matter causes the matter to lower its potential energy. Reasoning states matter in a material-environment; the matter slows down thus dropping its potential energy. ______________________________________________________________________ Newton just simply didn't understand that space was a vacuum. Believe or not I didn't do this for nothing. Once you compare matter to the vacuum of space it gives you, perpetual potential energy. Perpetuity of potential energy creates a circuit for matter, and that natural event is called gravity. When the perpetuity of potential energy is met with the vacuum of space the only theories these laws of potential energy and Newtonian laws can describe how vacuums affect as; is a conversion from perpetual potential energy to perpetual kinetic energy giving us an orbital circuit. The perpetual sum of potential energy equals to the perpetual sum of kinetic energy. A really good example of how gravity works is how tungsten doesn't just explode in Edison's light bulb. Tungsten begins to suppress itself when exposed to the vacuum through gravitational force increasing the amount needed to change its state of matter. Knowing this we could presume that when exposed to a vacuum that its complete spectrum of potential energy is directly increased. Accreditations to essential vacuums. To leave one quote to summarize what gravity is; I would like to say this. Gravity can not act upon other gravity it must be circuited from point a to b. Although gravity can act on matter, as it is a circuit, like copper to electricity. (a small excerpt about molecular gravity) If I were to explain the determinants of an outcome with a fifty fifty percent chance. Then I would start to explain that the first piece of information; determines the outcomes by randomly choosing the first time and choosing it one hundred percent of the time there after. Sense we know what we know about potential energy we can assume that when dealing with matter it can only affect other forms of matter, as long as force is providing through acceleration two objects will affect each other. This gravity alone could imprint and store energy from the accelerant. This alone could provide a blockade enough to explain the problems within quantum mechanics. Let's assume that gravity can store energy in vacuums like between molecules in which the space provided by definition is inert. What that means exactly is that the vacuum itself can not and will not move. Whereas vacuums themselves are massless thus volumeless, densless, and shapeless. Conjugating this reason as indisputable facts you can take it to say electricity can be held in superposition due to the lack of matter. This statement alone could explain superpositional frames of energy in quantum physics. Electricity exerts an opposite force on its circuit. Which is why it gets rid of electrons while also suspending the electrons. Though the circuit will store the imprint of that matter, like wax for a record player - down to copper for a voice. Audio particles can be shown by this same trait. Basically the gravitational space is being taken up, and any energy in any state of matter can just simply tell which path was better due to changing its state from kinetic energy to potential energy. The third law is very special to me. This came to be for the oddest and most backwards way it could come to fortuition. In highschool we were studying catalysts when I realized that when something like mentos is introduced to cola that liquid state of matter is very futile. The only way the reaction is possible is that the potential energy changes `state by lowering the potential energy of the liquids; that directly touch to some extent the catalyst. Anything beyond that natural event of potential energy lowering; Newtonian laws take over. Basically the high reaction of changing states of matter is because of the high kinetics that's interacting with the liquid which had that basic law of complex matter acting upon it. The important part of this is that -when you suck out a sandwich baggy... What's that bond keeping the sides together? More so to say the natural state of gravity at a kinetic state is bonding the matter together. To a point that it won't separate at least without breaking the vacuum itself. It's like real physicists are trying to tell you guys; that the only crushing force is force itself. Oh by the way force is a trait of matter. The only trait I can think that non matter does is that it changes potential energy in some way. catalytic potential problems P~ k#1-(k#2)=y P~ y+k#1=D x equals an expressed version of kelvin as r before or equal to the point matter changes states of matter; within an absolution of force.~ "but not anymore because now we just call it" kelvin.(Allan Adams) assume the potential state of matter. ________________________________ k#1- m#2 / k#2 - m#1 =g field ~P-k potential as kelvin to express the limit to which its state of matter can hold. ________________________________

you should have tried it with gpt 4 with code plugins which is much better at maths

Pokeball on the arm lol :D