On stackoverflow, they will answer aggressively: "Don’t post picture of code
Then, to fix it the user paste the code as text but with awful formatting. Then get another aggressive answer: “** DAMNIT, FORMAT YOUR CODE**”
I spent 45 mins with ChatGPT trying to give me the quick resolve for something querying with M.
It ended with me telling ChatGPT that if it worked for me, it would be fired because it kept trying to reoptimise my query, resulting in syntax and load errors, then “fixing” them by ignoring my query’s criteria.
I ended up going old school and taking an extra 30 mins to just figure it out myself. Now that I know how it’s done, it’s surprisingly easy to understand.
So I took that as a compliment; or ChatGPT just sucks at PowerQuery.
It probably learned, though. If anyone has transform queries around multi-level filtering criteria and ChatGPT helps, that’s because of my suffering.
Does chatGPT really learn from user inputs? I thought it was always restarting from the same base
In each session, the last several thousand words (from the user and AI) are kept in a context buffer to be used as additional inputs for the neural network. But I don’t think ChatGPT lets you choose the AI’s responses for that buffer, so you can’t really “train” it in any sense of the word. If you want that functionality, use LLaMa.
IDEs are bloat. I write my code using command line and concatenating each line into the file.
Please, that’s way too high level, I move the file to a hdd, pull it out and then use a fridge magnet to change individual bits. Works like a charm.
What kind of maniac posts a screenshot of their code instead of the code itself to ask for help tho
Make sure to print them out and re-photograph them on a wooden table!
