Every story and comment from the Hacker News API, in a layout borrowed from 2001.
A comment on OracleGPT: Thought Experiment on an AI Powered Executive. Parent comment
1. Past decisions and outcomes get into the context window, but that hasn't actually updated any model weights.
2. Your interaction possible eventually gets into the training data for a future LLM. But this is incredibly diluted form of learning.
There are no comments on this comment yet.
1. Past decisions and outcomes get into the context window, but that hasn't actually updated any model weights.
2. Your interaction possible eventually gets into the training data for a future LLM. But this is incredibly diluted form of learning.