alt Hacker NewsThey use Kimi and post-train it on the same stuff that anyone with a Github dump can feed it. They aren't doing anything that you can't do yourself.
Replies
whimsicalism • yesterday at 11:34 PM
why comment on something you clearly don't know anything about? it's on-policy RL trained not just on coding text
listen and learn :)
Dumping github into a model is not post training, thats pre training. And every base model already has all of github.
Composer post training is clearly very good, only second to Anthropic and OpenAI.
It does irk me a bit that they try to hide the fact that it's based on a chinese pretrained model though.