[–] maxbendick 19d ago ↗ What a bizarre README. From the top:> 3,500-Line Lightweight Agentic RL Framework for Training Agents with Real Harnesses!Ok, it's a framework. That can mean many things. Let's look at the "Key Features."> ~3,500 lines of code: We treat simplicity as the first principle.??? [–] whattheheckheck 19d ago ↗ What a bizarre comment
[–] fractorial 19d ago ↗ How does a _multi-trillion dollar company_ think this is good presentation? [–] rk06 19d ago ↗ it is made by Microsoft employees, not Satya. Microsoft employees have various degrees of freedom on what level of quality to targetwith absence of QA, quality is going downhill. thanks to AI mandate, quality is going downhill a lot faster
[–] rk06 19d ago ↗ it is made by Microsoft employees, not Satya. Microsoft employees have various degrees of freedom on what level of quality to targetwith absence of QA, quality is going downhill. thanks to AI mandate, quality is going downhill a lot faster
[–] ricardo_lien 19d ago ↗ how good is this? [–] owebmaster 19d ago ↗ I'd bet not even the vibecoders that prompted it know. But Claude said it's production ready
[–] owebmaster 19d ago ↗ I'd bet not even the vibecoders that prompted it know. But Claude said it's production ready
[–] RugnirViking 19d ago ↗ seems to be a toolkit for taking some LLM model and training/finetuning it further based on some agentic task (like painting, playing a video game, etc)
9 comments
[ 0.24 ms ] story [ 17.0 ms ] thread> 3,500-Line Lightweight Agentic RL Framework for Training Agents with Real Harnesses!
Ok, it's a framework. That can mean many things. Let's look at the "Key Features."
> ~3,500 lines of code: We treat simplicity as the first principle.
???
with absence of QA, quality is going downhill. thanks to AI mandate, quality is going downhill a lot faster