Know a great AI tool or AI news source? Submit it to AiByts
LessWrong23 min read

Personas in a Pre-Internet Language Model

David Africa & Nick LevineTLDRWe ran several persona experiments on Talkie, a 13B model trained only on English text from before 1931. We ran them alongside its modern twin (same architecture, trained on regular data as a control) and Llama-3.1-8B.Talkie can generalise maliciously.

By David AfricaLessWrong
Personas in a Pre-Internet Language Model

Read the full story

Originally published by LessWrong on Oct 13, 2026.

Read on LessWrong(opens in a new tab)

Comments

Sign in to join the discussion.

No comments yet — be the first to share your thoughts.