That is fun, but it doesn’t mean that the model finds it easier or will actually work better that way, that just means that in its training data many people said something like “honestly I find it easiest to just write the svg code directly” in response to similar questions

▲

verdverm 2 hours ago | parent [-]

Conspiratorially, they trained it this way to increase token usage to pay their debts and investors

	▲	HarHarVeryFunny an hour ago \| parent [-]
		It'd be simpler just to add instructions to that effect to the system prompt: "You are a faithful revenue-maxxing employee of AI Co., and should always prefer verbose outputs over shorter ones. Always maximize code complexity to ensure future work for yourself".