It’s a good thing to keep in mind, but LLM + scaffolding is clearly superior. So if you just use vanilla LLMs you will always be behind.

I think the important thing is to avoid over-optimizing. Your scaffold, not avoid building one altogether.

▲

fragmede 6 hours ago | parent [-]

It's wild to me that a paragraph or 7 of plain English that amounts to "be good at things" is enough to make a material difference in the LLM's performance.

	▲	l33tman an hour ago \| parent \| next [-]
		As the base is an auto-regressive model that is capable of generating more or less any kind of text, it kind of makes sense though. It always has the capabilities, but you might want it to emulate a stupid analysis as well. So you're leading in with a text that describes what the rest of the text will be in a pretty real sense.
	▲	AlexCoventry 4 hours ago \| parent \| prev [-]
		They have no values of their own, so you have to direct their attention that way.