GPT-4 / Compressing text - potential token saver

Don't know if anyone seen this but I find it super fascinating and its also a way to reduce token use. It appears that GPT-4 can compress text in a way that is better than any current compression software. But only for itself to decompress. You can use this prompt (None of this was in any way my idea), putting the text you want to compress after the ':'. I will list the prompt, the text I compressed, and what it compressed it to. Pretty wild.

compress the following text in a way that fits in a tweet (ideally) and such that you (GPT-4) can reconstruct the intention of the human who wrote text as close as possible to the original intention. This is for yourself. It does not need to be human readable or understandable. Abuse of language mixing, abbreviations, symbols (unicode and emoji), or any other encodings or internal representations is all permissible, as long as it, if pasted in a new inference cycle, will yield near-identical results as the original text:

Text I used:

It is a long established fact that a reader will be distracted by the readable content of a page when looking at its layout. The point of using Lorem Ipsum is that it has a more-or-less normal distribution of letters, as opposed to using 'Content here, content here', making it look like readable English. Many desktop publishing packages and web page editors now use Lorem Ipsum as their default model text, and a search for 'lorem ipsum' will uncover many web sites still in their infancy. Various versions have evolved over the years, sometimes by accident, sometimes on purpose (injected humour and the like).

The Result:

ℓestb_fact rdrDistrct✍️💻📄LrmIpsm:🔄nrmLtrDstr🆚"Cnthr, cnthr"; EngRdbl illusion. DTP/webEd🔄dfault. Srch➡️ LrmIpsm uncvr🌱sites. Vrsn⏳evolve,💥/💡(humr).

The chat log:

11 comments