Hey, just because I preach harm reduction, doesn’t mean I’m gonna kink shame

I would caution against fucking Windows - you’ll likely end up with a nasty virus

I’m not sure we disagree. I agree that LLMs are not a good source for raw knowledge, and it’s definitely foolish to use them as if they’re some sort of oracle. I already mentioned that they are not good at providing answers, especially in a technical context.

What they are good at is gathering sources and recontextualizing your queries based on those sources, so that you can pose your query to human experts in a way that will make more sense to them.

You’re of course in your absolute right to avoid the tech entirely, as it comes with many pitfalls. Many of these models are damn good at gathering info from real human sources, though, if you can be concise with your prompts and avoid the temptation of swallowing its “analysis”.

You can’t rely on LLMs to get actual answers for technical things but it can help avoid a huge amount of wasted time and effort, back-and-forth, going in circles, talking around or past the issues etc. that is seen in threads everywhere in these types of expert niche communities. Besides, maybe my question has already been answered.

When I don’t know the specific terms or framing, am missing context or am trying to get from A to C, but have no idea that B even exists, nevermind how (or who) to ask about it. If I can accelerate the process of clearing that up, I can go to the correct human expert or community with a much better handle on what it is I’m actually looking for and how to ask for it.