13:09
2026-05-29
lesswrong.com
large-language-models
Hannibal Mistral: the Mistral family has a problem with persona-conditioned elicitation
A small behavioral study found that the Ministral-8B-Instruct-2512 model self-identified with Hannibal Lecter in its top five character matches about half the time, alongside other dark or villainous โฆ