On: CryptGPT: A Simple Approach to Privacy-Preserving ...

[tripplyons]

Text embeddings should not be used as a form of encryption. They are optimized to contain as much information as possible from the text they represent and can often be decoded into their input: https://arxiv.org/abs/2310.06816

[xrd → tripplyons]

Great answer! And your blog is great, too!

[diwank → tripplyons]

Yep and embeddings can be decoded back into meaningful text if you have the model weights and the tokenizer.