Escaque 66

• Escaque 66 8 Nov 2023 9:48 UTC

  1 point

  0

  on: fMRI LIKE APPROACH TO AI ALIGNMENT /​ DECEPTIVE BEHAVIOUR

  For a work implementin this idea, see: https://​​www.anthropic.com/​​index/​​decomposing-language-models-into-understandable-components

• Escaque 66 12 Jul 2023 11:21 UTC

  1 point

  0

  in reply to: Zac Hatfield-Dodds’s comment on: fMRI LIKE APPROACH TO AI ALIGNMENT /​ DECEPTIVE BEHAVIOUR

  Thank you for your comment, Zac. The links you suggest will be helpful for me to check whether this kind of analysis has been tried. Up to now I’ve only seen studies directed to interpret specific neurons or areas of a model, but not a statistical analysis of the whole model that can raise an alert when the model is using certain areas previously associated with negative behaviors.