Improving Model Safety Behavior with Rule-Based Rewards

OpenAI developed a new method called Rule-Based Rewards (RBRs) to align models for safe behavior without needing extensive human data collection.

From the source
We’ve developed and applied a new method leveraging Rule-Based Rewards (RBRs) that aligns models to behave safely without extensive human data collection.
openai.com

Visit source ↗openai.com

Announced: 24 Jul 2024 09:00 UTC
Detected: 03 Aug 2026 21:11 UTC (+740d after)

Other stories

OpenAI · 31 AugPolimill builds Japan's next-generation public AI infrastructure

OpenAI · 31 AugA milestone in expanding access to AICompany news

OpenAI · 28 AugOur decision on Cursor following its acquisition by SpaceX

OpenAI · 28 AugSupporting Thailand’s next generation of AI startupsPartnership

Google Research · 27 AugPlanetary prediction engine: Automating global models via Earth AI

Research paper

OpenAI · 27 AugBetter answers, broader thinking: What students gain from ChatGPT and critical-thinking trainingResearch paper