Re:GPT-4
by bick_nyers on Thursday March 16, 2023 @03:21PM
(#35186957)
Yeah I was thinking that you can basically take each window of 8192 tokens or whatever and compress it to a smaller number, keep the compressed summary in the window, then any time it performs a search on previous summaries if it gets a hit it can then decompress that summary fully and use it. Basically integrate search and compression into the context window
[ Parent
| on HN ]
There are no comments on this comment yet.