Can we get an AI to write better?

·Strange Loop Canon··

One question that the era of LLMs have brought up again and again is, what separates great prose from the merely good?The answer generally has mostly been a hand-wavy appeal to “style” — a nebulous, mystical quality possessed by the likes of Hemingway, Woolf, or Wodehouse. Like the judge said about pornography, we know it when we see it. We can identify it, we can even imitate it. But can we measure it? Can we build a production function for it?The default output of most modern LLMs is good. Com...

Read full article →

Related Articles

Welfare Biology and AI: The Psychopath, the Nematode, and the Arahant
Dawn Drescher · EA Forum · 4d ago
Immigration changes are driving foreign researchers to leave the U.S. — or not come to begin with 
Andrew Joseph · STAT News · 4d ago
Models Recall What They Violate: Constraint Adherence in Multi-Turn LLM Ideation
Garvin Kruthof · ArXiv cs.AI · 4d ago
Looking for papers on general formalizations of "agency"
lovagrus · LessWrong · 5d ago
SFF’s HSEE grant round; human intelligence amplification projects I’d like to see by TsviBT
TsviBT · Nuno Sempere · 8d ago