Точка Синхронізації

AI Archive of Human History

A computational framework for human values
| USA | technology

A computational framework for human values

#Value alignment #Computational framework #Stuart Russell #Ethical AI #Machine learning #arXiv #Human values

📌 Key Takeaways

  • A new computational framework has been proposed to formalize human values for AI integration.
  • The research builds on Stuart Russell's concept of 'provably beneficial' artificial intelligence.
  • The study synthesizes insights from psychology and philosophy into a technical engineering context.
  • The framework aims to solve the 'alignment problem' by making AI behavior predictable and ethical.

📖 Full Retelling

Researchers and computer scientists released an updated paper on the arXiv preprint server in early 2024 to propose a comprehensive computational framework aimed at aligning artificial intelligence with human values. This theoretical breakthrough addresses the critical "alignment problem" by synthesizing long-standing research from psychology, philosophy, and the social sciences into a technical architecture. The project aims to move the industry beyond the pursuit of raw intelligence toward a model of AI that is provably beneficial to humanity, responding to growing concerns about the ethical risks posed by autonomous systems.

🏷️ Themes

Artificial Intelligence, Ethics, Technology

📚 Related People & Topics

Machine learning

Study of algorithms that improve automatically through experience

Machine learning (ML) is a field of study in artificial intelligence concerned with the development and study of statistical algorithms that can learn from data and generalize to unseen data, and thus perform tasks without explicit instructions. Within a subdiscipline in machine learning, advances i...

Wikipedia →

Stuart Russell

Topics referred to by the same term

Stuart Russell may refer to:

Wikipedia →

Ethics of artificial intelligence

The ethics of artificial intelligence covers a broad range of topics within AI that are considered to have particular ethical stakes. This includes algorithmic biases, fairness, accountability, transparency, privacy, and regulation, particularly where systems influence or automate human decision-mak...

Wikipedia →

🔗 Entity Intersection Graph

Connections for Machine learning:

View full profile →

📄 Original Source Content
arXiv:2305.02748v2 Announce Type: replace Abstract: In the diverse array of work investigating the nature of human values from psychology, philosophy and social sciences, there is a clear consensus that values guide behaviour. More recently, a recognition that values provide a means to engineer ethical AI has emerged. Indeed, Stuart Russell proposed shifting AI's focus away from simply ``intelligence'' towards intelligence ``provably aligned with human values''. This challenge -- the value alig

Original source

More from USA

News from Other Countries

🇵🇱 Poland

🇬🇧 United Kingdom

🇺🇦 Ukraine

🇮🇳 India