▲Guardian Angels: LLM Personalization for Productivity and Security(gwern.net)
28 points by andsoitis 8 hours ago | 4 comments
▲nshotton 6 minutes ago
I might be missing something here, but could this concept not also be used in the same way for harm? For example if a model is trained to replicated a sucessfull scammer?
▲great_wubwub 14 minutes ago
IDK, this seems like the next step towards uploading yourself to the cloud.
▲Avicebron 37 minutes ago
Why digital twins? What about the NetNavis from Megaman, just aligned to the users interests?
▲ai_fry_ur_brain 36 minutes ago
[dead]