We're thrilled to have our work with @SKTelecom featured on the Google DeepMind website. Together, we trained Gemma 3 4B to exceed frontier performance (GPT-4.1 and Claude Sonnet 3.7) at customer support moderation. 🔗 Read the full case study ⬇️

SK Telecom + Adaptive ML trained Gemma 3 4B with PPO obtaining impressive results, specially for a model of such size Learn more about how they did this adaptive-ml.com/post/sk-teleco…

Mind-blowing! 🤯 Gemma just showed how a small, open models can run circles around the big ones. SK telecom and Adaptive ML customized Gemma 3 4B to be cheaper, faster, and more accurate than models twice its size. Goal: Create a highly accurate, low-latency content moderation

We're proud to announce that gpt-oss-120b and gpt-oss-20b are now available on Adaptive Engine. Reinforcement fine-tune, evaluate, and serve OpenAI's first open-weight models since GPT-2 🚀

Julien Launay launched Adaptive to give data science teams in business enterprises their “RLOps tooling” to make reinforcement learning easier. Talking to Jon Krohn, Julien says, “Most of our users are data scientists who write Python codes to interface with the system”.

"Pre-training gets you knowledge, post-training gets you wisdom" - Julien Launay. 🎯 In this @SuperDataSci episode, Adaptive ML ML CEO Julien Launay reveals how RLAIF, RLVR and synthetic data are pushing the performance of SLMs to the frontier. youtube.com/watch?v=ocVCDH…