Are "Vintage LLMs" the start of a new humanistic field?

·Res Obscura··

Imagine talking to the collective consciousness of an era. Not the consciousness of any single person, but instead, a simulated collectivity based on billions of words produced within a historical time and place. What would you ask it? This is a hypothetical that is starting to become real thanks to recent work on what are called “Historical Language Models” or “Vintage LLMs” (one marker of a new field is that there is no fixed name for it yet!). The largest such model to date, Talkie-1930, was ...

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