Hacker News new | past | comments | ask | show | jobs | submit login

> You can't really train them to do math unless they've seen previous calculations with similar numbers in their training sets.

Generally true before xVal[1], but not exactly true after. Expect fairly basic advancement in the future to solve this problem completely.

1. https://arxiv.org/pdf/2310.02989.pdf




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

Search: