Osmosis is a platform for companies to fine-tune models that outperform foundation models with reinforcement learning.
Better, faster, and cheaper.
Learn more at osmosis.ai/contact
🚀 Next Wednesday, April 29, @daytonaio & @FounderCoHo are once again bringing together AI researchers at @Stanford for a high-signal evening focused on long-horizon, stateful agents, from infrastructure and RL pipelines to evaluation and benchmarking.
🎤 Speakers:
•
We recently added LoRA RL support for Qwen3.5 MoE models like Qwen3.5-122B.
The process involved merge conflicts, dependency issues, and a tricky race condition related to LoRA weight syncing.
We wrote up a post that goes into more detail and shares our work - link below!
We brought together 200+ founders, researchers, and engineers on Saturday for RL IRL at @ycombinator HQ!
At @Osmosis_AI, our belief is that RL is the missing piece for AI agents - so we had some friends share how they're applying RL today!
🧵of session recordings below:
Thank you all for coming to RL IRL @ycombinator!! 🫶🏻
I'm still in awe that we were able to pull this all together in < 1 month but this forum really validated to me just how bullish I am on big IRL events! (:
more from us soon <3
Had an great time at @ycombinator HQ running RL IRL - YC was at max capacity!
We wanted to focus on *applied* RL: how any company could use RL to improve agents, not just labs (i.e. what we do at @Osmosis_AI).
Thank you to all the attendees, as well as our amazing co-hosts!
I grew up in sf. I went to Cal, and have lived in sf my entire life. I’ve gone to over a hundred tech events, and have organized a few myself.
RL IRL was the best tech event I have ever gone to, by far.
Kudos to @adelwu_ and all the organizers and speakers.
Had an great time at @ycombinator HQ running RL IRL - YC was at max capacity!
We wanted to focus on *applied* RL: how any company could use RL to improve agents, not just labs (i.e. what we do at @Osmosis_AI).
Thank you to all the attendees, as well as our amazing co-hosts!