As decision models gain traction across the industry, Musubi has introduced an innovative approach to content moderation. On Tuesday, the company announced PolicyLM-1.7B, a lightweight decision model designed for real-time moderation, which is now available with open weights. This model aims to apply content policies written in plain English to messages in under 50 milliseconds.
Key Features of PolicyLM-1.7B
Musubi’s model is engineered to match the cost and speed of existing AI classifier systems used for moderation on most social platforms. However, its flexibility as a modern large language model (LLM) allows it to implement complex policies without requiring specialized training. Importantly, the model can adapt to policy changes without needing retraining, enabling human policy-setters to iterate as necessary.
Filip Jankovic, co-founder and chief AI officer of Musubi, emphasizes the model's utility for platform managers:
“"Product teams just want a better understanding of what’s happening on their platform, especially as the amount of content is exponentially increasing. Being able to label all of that in a very scalable, customizable way is extremely useful."
