kacperlukawski
Joined 4 years ago
Karma
104
Submissions
76
Member since
May 2
Joined 4 years ago
Embedding models usually have fewer parameters than the LLMs, and once we index the documents, their retrieval is also pretty fast. Using LLM as a judge makes sense, but only on a limited scale.
There is a whole movement around enshittification, and I see potential in this kind of app, even though it still seems to be a niche.