Skip to content
Better HN
Top
New
Best
Ask
Show
Jobs
Search
⌘K
RLHF from Scratch | Better HN
RLHF from Scratch
(opens in new tab)
(github.com)
75 points
onurkanbkrc
1mo ago
3 comments
Share
3 comments
default
newest
oldest
fauria
1mo ago
RLHF: Reinforcement learning from human feedback -
https://en.wikipedia.org/wiki/Reinforcement_learning_from_hu...
alansaber
1mo ago
Looks good. I am a big advocate for these hands on demos as being the best way for beginners to learn ML
vivzkestrel
1mo ago
i prefer things that can explain stuff to me visually like this post here
https://mlu-explain.github.io/neural-networks/
wouldnt it be nice if someone could actually cook every type of neural network in that format?
j
/
k
navigate · click thread line to collapse