You are viewing revision 1.0.0, last edited by RogerDearnaley

Having a (pre)training corpus of role-model exemplars of aligned AI behavior would be useful to fine-tune LLMs on and/or to add to their pretraining corpus. Creating this is a practical and useful alignment-related activity that we can work on now, and one which requires a rather different skillset from most other alignment work. Since aligned AI behavior is extremely selfless and moral compared to real human behavior, in ways that don't reflect evolutionary psychology, and snce aligned AGI/ASI doesn't exist yet, for now the AI role-models need to be fictional characters in a fictional setting.

This tag is intended for discussion of the best criteria/rubric for this fiction [an initial one will be posted shortly once complete], link-posts to fiction, or fiction posts. This could be new fiction, or curated preexisting fiction that has good exemplars of aligned AI role model. Preexisisting fiction that doesn't fully fit the rubric, but could be made to with minor edits, is acceptable as a linkpost along with notes of the rubric violations and suggested edits to fix them.

Posts tagged Aligned AI Role-Model Fiction