Comment by Nevermark
> Mostly the main limitation with LLMs is the imagination of the person using it. Ask the right questions and they get a lot more useful.
Completely agree.
We get waves of comments on HN downplaying model abilities or their value.
Many people don’t seem to explore and experiment with them enough. I have 3 screens. The left one has two models on it. The right one has a model & a web browser for quick searches. I work on the largest middle screen.
Extreme maybe, but I use them constantly resulting in constant discovery of helpful new uses.
I web search maybe 10% of what I did six months ago.
The quirks are real, but the endless upsides models deliver when you try things were unobtainium, from humans or machines, until LLMs.
I've only found useful answers for when I've begun something from completely zero. Things I've got even a reasonable grasp on I start to spot large dangerous holes a model very confidently claims is the right solution. Stuff like bringing camping stove inside a tent to avoid rainy weather, nevermind it being suicide at the same time.
>I web search maybe 10% of what I did six months ago.
Me too, though this is more driven by the total cliff-fall of web search result quality