Re:GPT-4
by kordlessagain on Tuesday March 14, 2023 @02:51PM
(#35156620)
Embeddings via ada-002 give us a way to update the model in real time. Using Weaviate, or another dense vector engine, it is possible to write "memories" to the engine and then search those with concepts at a subsequent inferencing step. The "document models" that the engine stores can be considered a "hot model".
Re:GPT-4
by bobvanluijt on Tuesday March 14, 2023 @03:04PM
(#35156823)
Yeah - it will become available as a multi2vec Weaviate module as well in due time.
Right now it's possible to simulate memory with additional context (eg system prompt) but it doesn’t represent existence experienced by the model. If we want to go deeper the models need to actually learn from their interaction, update their internal networks and have some capabilities of self reflection (ie "talking to themselves").
I'm sure that's highly researched topic but it would demands extraordinary computational power and would cause lot of issues by letting such an AI in the wild.