Oct. 28, 2023, 11:45 a.m. | Adnan Hassan

MarkTechPost www.marktechpost.com

Character-LLM is a trainable agent designed to simulate specific individuals by editing profiles and training models as personal replicas, replicating their unique experiences. An evaluation in a test playground involves interviewing these trained agents to assess their capacity to memorise characters and experiences. The approach explores the creation of personalised digital simulacra, indicating significant progress […]


The post This AI Research from China Introduces Character-LLM that Teaches LLMs to Act as Specific People such as Beethoven, Queen Cleopatra, Julius Caesar, …

act agent agents ai research ai shorts applications artificial intelligence china editing editors pick etc evaluation interviewing language model large language model llm llms machine learning people playground profiles research staff tech news technology test training training models

More from www.marktechpost.com / MarkTechPost

Founding AI Engineer, Agents

@ Occam AI | New York

AI Engineer Intern, Agents

@ Occam AI | US

AI Research Scientist

@ Vara | Berlin, Germany and Remote

Data Architect

@ University of Texas at Austin | Austin, TX

Data ETL Engineer

@ University of Texas at Austin | Austin, TX

Lead GNSS Data Scientist

@ Lurra Systems | Melbourne