@rishdotblog Congrats @rishdotblog ! Genuine question, what would this be useful for? Could this be used as a natural language search query for example? Is there a way to limit it only to SELECTS to avoid malicious updates etc?
"GPT is all you need for backend".
This was the most inspirational project from the hackathon over the weekend, hard to stop thinking about. LLM is a kind of equivalent of the Python interpreter, except it interprets English, and has knowledge and common sense.
This is one of those “wait, what?” moments… Here is a proof of concept that uses an LLM as a backend for a todo app. It doesn’t function as a structured database, but more as an oracle that is able to reason about its data, and can return it in novel ways back to the frontend!
We're releasing our @scale_AI hackathon 1st place project - "GPT is all you need for backend" with @evanon0ping @parkerjou
But let me first explain how it works:
@steveruizok@rsms ...but you may see some "speed" changes between the segments as you will move from a short handle to a long handle... Hope that helps!
@steveruizok@rsms the reason (t=.5) seems optically off is because your handle lengths are unequal on both sides. By making sure your handle lengths for each segment are the same length, your (t=0.5) will be in the middle again. By keeping the direction the same, the segments will still connect.