ART
AI
reinforcement learning framework
SHOW HN2025
116points
12comments
#647of 3,837 in 2025
Top 17%of 2025 by points
How HN took it
LovedMost comments that take a side are positive
5 positive, 3 neutral or asking, 0 mixed, 0 critical, out of 8 comments about the project. Thread score +0.48.
Docs: 3 for, 0 againstDesign: 1 for, 0 againstIdea: 1 for, 0 against
The thread, comment by comment
Each row is a top-level comment and its replies, in HN's order. Select a cell to open that comment on HN.
positive neutral or mixed critical about another commenter or something else the maker
What HN said
What people liked
Clear explanation of SFT versus RL
From 1 comment
Ok good questions here. By fine-tuning in this context I assume you mean "supervised fine-tuning", or SFT. SFT trains a model to produce a specific string of output tokens, given…
kcorbitt on HN
Useful documentation and comparison table
From 1 comment
the table with comparable models is a really great way to show off things here
jeffchuber on HN
Requests
Documentation for HTTP API endpoints such as /_train_model
From 1 comment
I really like this concept. Do you have documentation for the API response from the `/_train_model` endpoint?
tcdent on HN
Questions
How does RL differ from fine tuning and when to use each
From 1 comment
Thanks for sharing this! A couple of questions come to mind: - How does training with RL differ from fine tuning? - When would it make sense to fine tune instead of using RL?
someguy101010 on HN
Alternatives named
GRPOTrainer
From 1 comment
verl
From 1 comment