[mateo1]

I'm not a programmer, and when I write a program it's imperative that it's structured right and works predictably, because I have to answer for the numbers it produces. So LLMs have basically no use for me on that front.

I don't trust any LLM to summarize articles for me as it will be biased (one way or another) and it will miss the nuance of the language/tone of the article, if not outright make mistakes. That's another one off the table.

Although I don't use them much for this, I've found 2 things they're good at: -Coming up with "ideas" I wouldn't come up with -Summarizing hundreds (or thousands) of documents from a non-standard format (ie human readable reports, legal documents) that regular expressions wouldn't work with, and putting them into something like a table. But still, that's only when I care about searching or discovering info/patterns, not when I need a fully accurate "parser".

I'm really surprised on how useless LLMs turned out to be for my daily life to be honest. So far at least.

[curtisblaine]

How do you ask an LLM to come up with good ideas? Everytime I try to use ChatGPT for idea generation, the results are subpar, but maybe it's me / my prompts.

[influx]

I usually will give a bullet list of ideas I already had and ask the LLM to add N more to the list, most of them will be garbage, but there might be 1 that I hadn't thought of, and I'll sort of recursively add that to the list, and continue that until I get what I need.