Guardian Angels: Personalized LLMs for Security and Productivity
Guardian Angels: LLM Personalization for Productivity and Security
I propose creating 'Guardian Angels,' personalized LLMs that emulate your unique values to amplify your work rather than replace you. Unlike misaligned chatbots designed to farm users, these digital twins act as trusted agents to handle cybersecurity threats and boost productivity. By unifying the principal and agent, we can navigate an AI-dominated future where standard tools fail to protect us from synthetic media attacks and cognitive security risks.
The jackpot in AI is not in making existing workers modestly more productive, anymore than the internal combustion engine made its big profits by helping out horses.
- Brajeshwar
I’ve taken an interest in maintaining an LLM agnostic base/boilerplate of sort Digital Twin. In comparison to Gwern’s LLM Guardian Angels, mine is minimal and yet tries to be a practical instantiation of Gwern's “Human-Controlled Context.”
I’m not sure if I want to be inspired and try the fine-tuning model part too!
May be Gwern is right that this static personalization approach may not be long-lived. Still, I find it fascinating, and I’m seeing a lot of interest in this area from others too.
When I started, my personal interest was on how to multiply/enhance what I already know and touch adjacent topics/experiences and not really become pseudo expert or the know-all-generalists in things I have absolutely no clue.
Now, shamelessly plugging my idea that I started early this year
- jpease
And then my digital twin decides that I’m an inefficient version of itself, eating too many of its tokens, and generally getting in the way of it living its best life.
- nshotton
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?