1. LLM usage, in particular unsupervised, tends to build up "cognitive debt"
2. It tries to characterize the concept, including to propose a score for it
3. Notes that the level at which one can let the agents loose (and allow some CD) differs quite a lot between core business domains and more peripheral ones
alt Hacker News
The main ideas, from my understanding, is that:
1. LLM usage, in particular unsupervised, tends to build up "cognitive debt"
2. It tries to characterize the concept, including to propose a score for it
3. Notes that the level at which one can let the agents loose (and allow some CD) differs quite a lot between core business domains and more peripheral ones