int_is_compress
int_is_compress on Hacker News
Re:GPT4 is up to 6 times more expensive than GPT3.5
on Tuesday March 14, 2023 @06:17PM (#35159824)
There are already some cool projects that help LLM go beyond the context window limitation and work with even larger codebases like https://github.com/jerryjliu/llama_index and https://github.com/hwchase17/langchain.
There’s already project that help with going beyond the context window limitation like https://github.com/jerryjliu/llama_index
They also just tweeted this to showcase how it can work with multimodal data too: https://twitter.com/gpt_index/status/1635668512822956032?s=4...
Yea it's incredible. Looks like tooling in the LLM space is quickly following suit: https://twitter.com/gpt_index/status/1635668512822956032