Conversation

Replying to
This is extremely cool but I wouldn't call it that sophisticated, it's a first draft of the approach. I feel like you could do this with maybe a third of the tokens, for starters
1
11
Show replies
Replying to
The ability for GPT to understand long form meaning is insane. Soon it's going to call our words "hallucinations" and we would deserve it
2
Replying to
something about the tone of the prompt really gets me like, really trying to help a nascent ai grow into it’s abilities by priming it with its own behavioral patterns and faults… and it’s working???
1
1
1
Show more replies