Hacker Newsnew | past | comments | ask | show | jobs | submitlogin

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



Consider applying for YC's Fall 2025 batch! Applications are open till Aug 4

Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact

Search: