Upgrading the Moderation API with our new multimodal moderation model

OpenAI Blog2024-09-26 18:000 views

We’re introducing a new model built on GPT-4o that is more accurate at detecting harmful text and images, enabling developers to build more robust moderation systems.

Source：https://openai.com/index/upgrading-the-moderation-api-with-our-new-multimodal-moderation-model

My favorites

PreviousOperation “STORM-2035”: Iran-origin influence activity NextMinnesota’s Enterprise Translation Office uses ChatGPT to bridge language gaps

Node.js Share Card Cache: 3 Contracts for Replaceable Open Graph Images

A media catalog that removes backgrounds from product photos should cache Open Graph share card images independently of

0dev.to Node

App Backup Retention: Private Object Storage Lifecycle Deletion After 30 Days

For a game backend, a private object-storage bucket with dated backup keys and a day-based lifecycle rule is a sensible

0dev.to Node

Playwright Agents Six Months Later: The Brutal Lessons That Made Them Better

Last time , my planner burned 156k tokens, 78% of my window, planning one feature. If I asked it to plan the next featur

0dev.to Testing

ProfoundSyntax—a developer community in beta. Help me find the rough edges.

Hey DEV We've been building ProfoundSyntax , a developer community that's now in beta. It's a place for programming ques

0dev.to Testing

Kubecost vs. OpenCost in 2026: Production Architecture & Setup for Kubernetes FinOps

As containerized workloads scale across enterprise production clusters, understanding where container spend goes is one

0dev.to Kubernetes

mock_api_assets: a fake backend from JSON fixtures for Dart and Flutter

Front-end work often starts before the backend is ready. The API is still being designed, or it exists but you are on a

0dev.to OpenSource