Hacker Newsnew | past | comments | ask | show | jobs | submitlogin

It should be simple to fit a style-filter onto an LLM. Curious why we still don't have that, and why everybody is using the default.
 help



I think the idea that there could be such a thing as a “style” filter misunderstands what style is. It’s not about avoiding buzzwords, it’s about tone, empathy with a reader, the layered and often unconscious will to express certain ideas with a specific flavor, and the idiosyncrasies that come from being a particular person who has lived a particular life with its own odd mix of influences and experiences.

Humans fail at good style more radically than LLMs do, and LLMs are on average better writers than people. But good style requires particularity and history in a way that a model could never achieve with just a filter.

The closest I’ve gotten to getting an LLM to write well was when I gave it an intellectual biography along with its writing assignment. But even that fails over longer context, because attention makes it very hard to build up narrative (even just conceptual narrative) in a compelling way that extends past the length of a short blogpost. Past a certain point you always end up back in the uncanny valley with that weird lack of cohesion and the unjustified contrastives, tricolons, and empty cliches.




Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact

Search: