| ▲ | Guardian Angels: LLM Personalization for Productivity and Security(gwern.net) | |
| 46 points by andsoitis 10 hours ago | 3 comments | ||
| ▲ | nshotton 2 hours ago | parent | next [-] | |
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 2 hours ago | parent | prev | next [-] | |
IDK, this seems like the next step towards uploading yourself to the cloud. | ||
| ▲ | Avicebron 2 hours ago | parent | prev [-] | |
Why digital twins? What about the NetNavis from Megaman, just aligned to the users interests? | ||