Guardian Angels: LLM Personalization for Productivity and Security
- I discuss a package of techniques and proposals to accomplish such ‘guardian angels’; dynamic evaluation of LLMs combined with active learning and elicitation and heavy inner-monologue search/data-augmentation.
- Powerful LLMs will be deployed at global scale in the next few years, and will dominate the
Unverified
- I discuss a package of techniques and proposals to accomplish such ‘guardian angels’; dynamic evaluation of LLMs combined with active learning and elicitation and heavy inner-monologue search/data-augmentation.
- Powerful LLMs will be deployed at global scale in the next few years, and will dominate the
Sources: Gwern