Re:Creating AI assistant with GPT and Ruby and Redis using e...
by fzliu on Wednesday April 26, 2023 @05:58PM
(#35720582)
Even with an incredibly long context window (say, 1M tokens), attention still suffers from a problem with long-term dependencies. This is probably why OpenAI hasn't publicly released their 32k token length model just yet.
[ Parent
| on HN ]
Re:Creating AI assistant with GPT and Ruby and Redis using e...
by Der_Einzige on Wednesday April 26, 2023 @06:18PM
(#35720764)
I think they haven't released it because the capabilities it has are simply too powerful when combined with a vectorDB.
Re:Creating AI assistant with GPT and Ruby and Redis using e...
by sparker72678 on Wednesday April 26, 2023 @06:21PM
(#35720791)
Maybe. It's also probably staggeringly expensive to run.