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

This has very little resemblance of SWE-grep haha. At least fine-tune a small pre-trained LLM or something on a retrieval dataset. But no, this literally tries to train a small RNN from scratch to retrieve results given a natural language query...


Consider applying for YC's Winter 2026 batch! Applications are open till Nov 10

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