New models: Sexual, Discrimination, Violence, and Self-harm
![New models: Sexual, Discrimination, Violence, and Self-harm](/blog/content/images/size/w1200/2024/02/text_analysis.png)
We've just made 4 new classifier models availabel in your dashboards.
We've just made 4 new classifier models availabel in your dashboards.
OpenAI have just released their latest model GPT-4o-mini. We're excited about the updated model and are already using it for AI Agents on Moderation API. All existing AI Agents have been upgraded to GPT-40-mini automatically. As a result you should see: * Higher accuracy and better performing AI agents.
I'm excited to announce the launch of the upgraded analytics dashboard that will provide deeper insights into user behaviour and content trends on your platform. With a privacy-first design, these analytics tools will allow you to track and understand how people are using and potentially abusing your platform,
You can now add custom label filters for review queues. This allows you to create queues like: * Show items with the POSITIVE label to find positive user comments. * Show items where the TOXICITY label has a score between 20% and 70% to find content where the AI is uncertain. * Filter
I'm excited to announce that you can now moderate images with moderation API. Setting up image moderation works similarly to text moderation. You can adjust thresholds, and disable labels that you do not care about when flagging content. We offer 9 different labels out of the box -