HN
Hacker News
Top
New
Best
Ask
Show
Jobs
Comment by bevekspldnw | Hacker News Reader
Full thread
bevekspldnw
·
How much of this is RL’ing a good coding model on every CVE ever?
View on HN
sometimelurker
·
most it this comes from the pretrain imo. just scale + some RL = mythos
Reply on news.ycombinator.com