We’re releasing Safety Gym, a suite of environments and tools for measuring progress towards reinforcement learning agents that respect safety constraints while training.
Recommended
Operation "Doppelganger": Russian influence activity targeting UkraineOpenai Everyday work with ChatGPT WorkOpenai Romance scams: AI-enabled romance scam workflowsOpenai Will Hurd joins OpenAI’s board of directorsOpenai Statement from the OpenAI Board of Directors on the Nonprofit Commission ReportOpenai Simplifying, stabilizing, and scaling continuous-time consistency modelsOpenai
Security Implementation for Responsible AI: A Practical FrameworkCybersecurity Exchange
Vulnerability Management in Container ImagesAquasec
A New Approach for Coding Agent SafetyDocker
How to Create Safety Training Videos with AISynthesia
Neo: Zero-downtime migration from CDK, Terraform & Azure ARMPulumi
AI governance: Build responsiblyWeb
Data Scientist - AI SafetyElevenlabs
Safety Engineer - Free Tier AbuseElevenlabs
Lima v2.1: macOS guests and enhanced AI agent safetyCncf
RewardBench 2: Advancing Reward Model EvaluationCohere
The Multilingual Divide and Its Impact on Global AI SafetyCohere
Sleeper Agents: Training Deceptive LLMs that Persist Through Safety TrainingAnthropic
Trustworthy agents in practiceAnthropic
How to Set Up AI Avatar Consent, Safety & Brand ControlsHeygen
