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

first, this is amazing!

second, how does one increase the context window without requiring obscene amounts of RAM? we're really hitting the limitations of the transformer architecture's quadratic scaling...



Chain of agents seems to be a promising approach for splitting up tasks into smaller parts and then synthesising the results[1]

[1] https://research.google/blog/chain-of-agents-large-language-...




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

Search: