Thread

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

103 points · 110 comments · yu3zhou4

ForHackernews · 1790506674 · focus · HN ↗
In my view, these models should never be set up to output first-person "experiential" (from the abstract) language. It's too easy to humans to anthropomorphize software that presents itself as having an identity.
The AI companies have chosen to package LLMs as friendly chatbots because they know that will be engaging for humans, but it's manipulative dark pattern. An honest LLM interface would sound like the computer off Star Trek.
1. yu3zhou4 · 1790507112 · focus · HN ↗
  The strange thing is that the base models (before RLHF) use the "experiential" voice, even though they are not incentivized to do that.
  1. gwerbin · 1790507605 · focus · HN ↗
    It doesn't seem that strange when you consider these things are trained on millions and millions of conversations, both real and fictional.

Unofficial Hacker News client; not affiliated with Y Combinator.