> prompt engineering
The only group of people more delusional than the AI doomsday screamers are those who think playing around with LLMs is "engineering".
ChatGPT-4o vs. Math
81–90 of 182 posts
Re: ChatGPT-4o vs. Math
#82I have a theory that the more you use ChatGPT, the worse it becomes due to silent rate limiting - farming the work out to smaller quantized versions if you ask it a lot of questions. I’d like to see if the results of these tests are the same if you only ask one question per day.
that's an interesting hypothesis, I suppose one can make N calls to the API and look if the distribution of wrong answers is skewed towards the later portion of the API calls
Re: ChatGPT-4o vs. Math
#83> prompt engineering The only group of people more delusional than the AI doomsday screamers are those who think playing around with LLMs is "engineering".
I prefer the term "making shit work"
Re: ChatGPT-4o vs. Math
#84I posted the same 'Zero-Shot Chain-of-Thought and Image' to ChatGPT-4o and it made the same error. I then followed up with 'Your math is good but you derived incorrect data from the image. Can you take another look and see if you can tell where the error is?'. It figured it out and corrected it: Let's re-examine the image and the data provided: * The inner radius r1 is given as 5cm * The outer radius r2 is given as 1…
I mean I could see my kid making this exact mistake on a word problem, so I suppose we've achieved "human like" reasoning at the expense of actually getting the answer we want?
Re: ChatGPT-4o vs. Math
#85I'm grateful this is a simple blog post rather than a 20-page arXiv paper with dozens of meaningless graphs. Or worse, a 20-deep Twitter thread.
well, I got banned on twitter 3 times in the past 30 days so no more threads
Re: ChatGPT-4o vs. Math
#86Earlier quoted context omitted.
I think LLMs will need to do what humans do: invent symbolic representations of systems and then "reason" by manipulating those systems according to rules. Here's a paper working along those lines: https://arxiv.org/abs/2402.03620
Is this what humans do?
Think of all the algebra problems you got in school where the solution started with "get all the x's on the same side of the equation." You then applied a bunch of rules like "you can do anything to one side of the equals sign if you also do it to the other side" to reiterate the same abstract concept over and over, gradually altering the symbology until you wound up at something that looked like the quadratic formula or whatever. Then you were done, because you had transformed the representation (not the value) of x into something you knew how to work with.
Re: ChatGPT-4o vs. Math
#87I posted the same 'Zero-Shot Chain-of-Thought and Image' to ChatGPT-4o and it made the same error. I then followed up with 'Your math is good but you derived incorrect data from the image. Can you take another look and see if you can tell where the error is?'. It figured it out and corrected it: Let's re-examine the image and the data provided: * The inner radius r1 is given as 5cm * The outer radius r2 is given as 1…
I mean I could see my kid making this exact mistake on a word problem, so I suppose we've achieved "human like" reasoning at the expense of actually getting the answer we want?
I tried to work out the problem myself first (using only the text) and accidentally used the diameter as the radius just like ChatGPT! Granted I haven't really tackled any maths problems for many years though.
Re: ChatGPT-4o vs. Math
#88Earlier quoted context omitted.
Have you tried actual math tools like wolfram alpha? My response to attempts to use llms to do math is usually, use the right tool for the job.
"a PhD level understanding of computer aided geometric design" could you elaborate? I found chatgpt to pretty useful in high level understanding of where the topics stand in the grand scheme of things kinda like a pre-google -- it helps me navigate what to google let's ask gpt4o You're an expert math researcher. - Give me an overview of topos theory - What are the main unsolved problems - What is the point of it? - W…
Specifically, I was trying to get help from ChatGPT to give a simple formula for the location of the P3 control point of a degree 3 (or higher) Bézier curve in order to maintain G3 continuity (given the derivatives at the end of the adjacent curve). There's a very straightforward equation for the P2 control point for G2 continuity, but I've been struggling to understand the math for G3 continuity.
I've found a ton of research papers and information, but most of it is quickly beyond my ability to digest.
For G2 constraints, there is simple equation:
K(t0) = ((n-1)/n)*(h/a^2)
Where n is the degree of the curve, a is the length of the first leg of the control polygon, and h is the perpendicular distance from P, to the first leg of the control polygon. K(t0) is the curvature at the end point of the adjacent curve.
Depending on what you want to do, it's easy to solve for K(t0), a or h. I would like something this simple for G3.
Re: ChatGPT-4o vs. Math
#89Earlier quoted context omitted.
This speaks to a deeper issue that LLMs don’t just have statistically-based knowledge, they also have statistically-based reasoning. This means their reasoning process isn’t necessarily based on logic, but what is statistically most probable. As you’ve experienced, their reasoning breaks down in less-common scenarios even if it should be easy to use logic to get the answer.
Does anyone know how far off we are having logical AI? Math seems like low hanging fruit in that regard. But logic as it's used in philosophy feels like it might be a whole different and more difficult beast to tackle. I wonder if LLM's will just get better to the point of being indistinguishable from logic rather than actually achieving logical reasoning. Then again, I keep finding myself wondering if humans actuall…
We could get there if current LLM's managed to prepare some data and offload it to a plugin, then continue on with the result
* LLM extracts the problem and measurements * Sends the data to a math plugin * Continues its reasoning with the result
Re: ChatGPT-4o vs. Math
#90[dead]