[ir77]

last week i broke down and bought the 20$ subscription because i was excel lazy and wanted to see what supposedly state of the art AI could do to help me parse my kids baseball team's statistic... and boy am i confident more than ever that humanity is not doomed and there won't be AI taking over jobs anytime soon.

the amount of time i spend typing out "you've changed something i didn't ask" is incredible, the only positive i get is that it's fun to verbally abuse AI for how inaccurate and deliberate with errors it is.

i would not take a single answer from chatgpt without actually doing a sanity check. if it throws up on an excel that has 12x30 data matrix of one dimensional data, i couldn't imagine the garbage it spews out if you're using it to modify something actually business essential.

[jstanley]

You don't want to ask AI to directly manipulate 360 distinct data points for the same reason you wouldn't ask a human to do that.

Get it to write a script to process the data instead.

[aothms]

In my experience more often than not it'll do that for you and run the code to give you the answer.

E.g just now I ran:

~~~

What's the inverse of this matrix?

[[0.0759688880587972, 0.3299493758880664, 0.14599823333009276, 0.09897577338235164], [0.7478951343477207, 0.9006422280032432, 0.3137352150172843, 0.5974301357799204], [0.5568700534103693, 0.648666832906366, 0.5280912469659284, 0.5753861797637815], [0.7905984807343551, 0.053757547259005944, 0.9632727273522135, 0.44727851917969785]]

~~~

Reasoning output:

~~~

The user is asking for the inverse of a matrix. Since they want the result, I will compute it and present it as a matrix in Markdown. I’ll use Python for the calculation but won’t include any code in the final answer. It’s best to show the resulting matrix in Markdown so the user sees only the output, as requested. I’ll use Python to compute it and then provide the result without extra code.

import sympy as sp import numpy as np

# define the matrix M = np.array([ [0.0759688880587972, 0.3299493758880664, 0.14599823333009276, 0.09897577338235164], [0.7478951343477207, 0.9006422280032432, 0.3137352150172843, 0.5974301357799204], [0.5568700534103693, 0.648666832906366, 0.5280912469659284, 0.5753861797637815], [0.7905984807343551, 0.053757547259005944, 0.9632727273522135, 0.44727851917969785] ], dtype=float)

# calculate inverse invM = np.linalg.inv(M)

invM

~~~

And then I get a nicely formatted latex matrix as the final outcome.

(edit: that's 04-mini-high)