this post was submitted on 27 Jan 2025
18 points (100.0% liked)
Hacker News
626 readers
553 users here now
Posts from the RSS Feed of HackerNews.
The feed sometimes contains ads and posts that have been removed by the mod team at HN.
founded 5 months ago
MODERATORS
you are viewing a single comment's thread
view the rest of the comments
view the rest of the comments
Interesting! I wonder if this new method of training will improve performance or if it only benefits the efficiency of training the model. I don’t know too much about R1, and I had no idea ByteDance was also working on LLMs.