Your boy has seen the future in a (mostly broken) Discord bot. When the tooling catches up, things will get nuts.
really liking the idea of a CHAT stack. fantastic explanaiton and first explanation ive seen of promt tokens vs completion tokens. great stuff Jon!
I'm doing a writeup on smaller models that can run locally. That field is advancing rapidly, and it's impossible to handwave it away like OpenAI's brute force magic "in the cloud".
Thank you. This is very helpful.
Jon, I have a question (or anyone can answer). So In the four-stage chatbot setup, you show a CONTENT icon that I think is the user (or company) specific content that is separate from a public LLM. I'm wondering if I understand this correctly. That CONTENT store is a vector database of imported content that has be converted to embeddings (vectors). This makes it possible for a user to leverage the strength of an LLM as a conversation interface to get an answer from the CONTENT store?
I'm just trying to understand this. I assume this is for example what PINECONE.IO is offering as a solution provider.
This is what LoRAs are supposed to handle, isn't it?
The other thing people need, even if they don't realize it, is not becoming dependent on the whims of OpenAI.