Get the latest tech news

Show HN: ART – a new open-source RL framework for training agents

OpenPipe ART (Agent Reinforcement Trainer): train LLM agents - OpenPipe/ART

Get the Android app

Or read this on Hacker News

Read more on:

Photo of Art

Art

Photo of training agents

training agents

Photo of source RL framework

source RL framework

Related news:

Art of the Hedgerow

Hori's Piranha Plant Switch 2 camera is a work of art

The Art of DJing: Avalon Emerson (2019)

« Why wait for Prime Day? The Galaxy Watch 7 just crashed to its lowest price EVER at Amazon

Warning systems for floods, hurricanes, and famine are suffering from Donald Trump’s data purge | By gutting USAID, the Trump administration has cut off access to data people relied on to warn people about weather disasters and food shortages around the world. »