Do you read a song on demand when you are singing the lyrics verbatim?
abruptly8951
joined 1 year ago
It's definitely not indexed, we use RAG architectures to add indexing to data stores that we want the model to have direct access to, the relevant information is injected directly in the context (prompt). This can somewhat be equated to short term memory
The rest of the information is approximated in the weights of the neural network which gives the model general knowledge and intuition..akin to long term memory
You seem a bit troll-y too but I'll bite.
The only one suggesting to add women because they are women is the edgy beb. The change I want to see is edgies being made to feel small. I have achieved based on their anemic come back :)
The person starting this thread wants to see the world you're suggesting I create. And in doing so has opened a whole new class of YouTuber for our dear OP to explore..the analogy about fish, fishing and teachers come to mind
Ooh edgy, say more
This is an extremely odd outlook to have. Good luck with it.
Unfortunately the answer to your question is to not post at all, though if your contributions are worthwhile then that is not an excellent solution
Yup, that seems to be about all it's got going for it
Just as powerful and far less buttons imo. I can write a markdown doc in much less time than a word doc.
What does word offer that isn't easier with markdown?
Obsidian? Also havent used it but logseq
This sounds like a fun project "samples of chemistry"
There's is a huge difference though.
That being one is making hardware and the other is copying books into your training pipeline though
The copy occurs in the dataset preparation.
Ok bud