Learning from human preferences

📰 OpenAI News

OpenAI and DeepMind developed an algorithm that infers human preferences by comparing two proposed behaviors

advanced Published 13 Jun 2017
Action Steps
  1. Collaborate with safety teams to identify complex goals
  2. Develop algorithms that can infer human preferences from comparisons
  3. Test and refine the algorithm with human feedback
  4. Integrate the algorithm into AI systems to improve safety and alignment
Who Needs to Know This

AI researchers and engineers on a team can benefit from this algorithm to build safer AI systems, and product managers can use it to develop more aligned AI products

Key Insight

💡 Inferring human preferences from comparisons can help build safer AI systems

Share This
🤖 New algorithm infers human preferences from comparisons! 🚀

Key Takeaways

OpenAI and DeepMind developed an algorithm that infers human preferences by comparing two proposed behaviors

Full Article

One step towards building safe AI systems is to remove the need for humans to write goal functions, since using a simple proxy for a complex goal, or getting the complex goal a bit wrong, can lead to undesirable and even dangerous behavior. In collaboration with DeepMind’s safety team, we’ve developed an algorithm which can infer what humans want by being told which of two proposed behaviors is better.
Read full article → ← Back to Reads

Related Videos

5 Levels of AI Agents - From Simple LLM Calls to Multi-Agent Systems
5 Levels of AI Agents - From Simple LLM Calls to Multi-Agent Systems
Dave Ebbelaar (LLM Eng)
How To Use Google Omni | Real AI Avatar Videos Kaise Banaye | Full Tutorial
How To Use Google Omni | Real AI Avatar Videos Kaise Banaye | Full Tutorial
Digital Marketing Guruji
What exactly is a diffusion language model?
What exactly is a diffusion language model?
Vizuara
AI Named the 2026 FIFA World Cup Winner (Shocking Prediction)
AI Named the 2026 FIFA World Cup Winner (Shocking Prediction)
AI Master
Our vibe coded projects that actually work | The Vergecast
Our vibe coded projects that actually work | The Vergecast
The Verge
5 Insane Claude Cowork Use Cases That Feel Illegal
5 Insane Claude Cowork Use Cases That Feel Illegal
Charlie Chang