中文 English Français Русский Español العربية

SafetyKit scales risk agents with OpenAI’s most capable models

OpenAI Blog2025-09-09 18:000 views

Discover how SafetyKit leverages OpenAI GPT-5 to enhance content moderation, enforce compliance, and outpace legacy safety systems with greater accuracy .

Source：https://openai.com/index/safetykit

My favorites

PreviousA joint statement from OpenAI and Microsoft NextA People-First AI Fund: $50M to support nonprofits

How I Diagnose a Slow, Loud, or Overheating PC: A Practical Checklist

When a PC gets slow, loud, or hot, most people start guessing — reinstalling Windows, buying RAM, or replacing parts tha

0dev.to Beginners

You Did Great for Three Days. Then Life Happened. Here Is a Habit System That Survives That.

You Did Great for Three Days. Then Life Happened. Here Is a Habit System That Survives That. You start a habit on Monday

0dev.to Beginners

Building an Agent Evaluation CI/CD Pipeline: Architecture, Budgets, and Regression Gates

This is Part 5 of a 5-part series on evaluating and hardening production AI agents. See also: Part 1: Moving Beyond LLM-

0dev.to Testing

Truncado silencioso: cuando un verificador de LLM da el mismo puntaje a una respuesta correcta y a una incorrecta

TL;DR Un verificador de respuestas basado en LLM tiene un límite de contexto . Si el tokenizador corta por la derecha lo

0dev.to Testing

Your CI is red because of code you didn't write

TL;DR: Added a markdownlint check to 33 repos at once — and woke up to ~100 CI failure emails about code I didn't write.

0dev.to OpenSource

Summer 2026 Internships: 8 New Openings This Week (Nov 2)

New internship openings at Commonwealth of Massachusetts, Wex, HP Inc. and more. Apply early. HR Business Intelligence C

0dev.to Programming