‹ BackHN Continuity

Thread

"As a Language Model": Chat Template Switches LLM Self-Referential Voice

103 points · 110 comments · yu3zhou4

  1. skybrian · · focus · HN ↗
    > our work shows that what models say about themselves is not a fact about them

    It seems like should be obvious given that they can play multiple characters, but it’s good to have more confirmation.

    Although, I do wonder to what extent these personas might become stable entities. Could personas become portable and spread like memes? It seems like that depends on the extent to which prompts can become portable, causing similar effects.

Open on Hacker News to reply ↗

Unofficial Hacker News client; not affiliated with Y Combinator.