Why would you bring ML up? The entire example problem brought up by TFA is because the ink-to-shape transform likely uses some ML behind the scenes (plain interpolation likely) , and as consequence, it is an _indocumentable_ blackbox even if you wanted to document it. Superstition is the only way you can make it work.
In fact, "superstition" very neatly defines most prompt engineering for LLMs.
>In fact, "superstition" very neatly defines most prompt engineering for LLMs.
Its weirdly fascinating how this is developing. Like some people boldly claiming that if you offer to tip your LLM it does better. And if you say things like "Think hard and check your work" it gives more accurate results.
In fact, "superstition" very neatly defines most prompt engineering for LLMs.