AI Zeitgeist

Askell et al. on AI

3 quotes from Askell et al. on the wall, 2021, newest first. Each one is verbatim and links to where it was said. Sources include arXiv.

Askell et al. in the Archive

  1. Harmless

    Canon#safety

    arXivA General Language Assistant as a Laboratory for Alignment

  2. Helpful

    Canon#safety

    First of the three H's: helpful, harmless, honest.

    arXivA General Language Assistant as a Laboratory for Alignment

  3. Honest

    Canon#safety

    arXivA General Language Assistant as a Laboratory for Alignment