OpenAI, the leading artificial intelligence (AI) research organisation, is taking a proactive approach to address the potential risks associated with 鈥渟uperintelligent鈥� AI systems. In a recent blog post, Ilya Sutskever, OpenAI鈥檚 chief scientist and co-founder, and Jan Leike, a lead on the alignment team, highlighted the need for research and development in controlling and steering advanced AI that surpasses human intelligence.
听
Anticipating the Arrival of Superintelligent AI
听
Sutskever and Leike expressed their belief that AI systems with intelligence surpassing that of humans may become a reality within the next decade. They emphasised the importance of preparing for such an eventuality as these superintelligent AI systems might not inherently possess benevolence or align with human values.
To ensure the safe and responsible development of AI, OpenAI recognises the need for robust strategies to control and restrict potentially rogue superintelligent systems.
听
Addressing the Challenge of Steering Superintelligent AI
听
The newly formed Superalignment team, led by Ilya Sutskever and Jan Leike, will dedicate their efforts to advancing the field of 鈥渟uperintelligence alignment.鈥� This team will have access to a significant portion of OpenAI鈥檚 computational resources, approximately 20% of the company鈥檚 existing compute capacity. By bringing together researchers and engineers from OpenAI鈥檚 alignment division and collaborating with experts from various other organisations, the team aims to tackle the core technical obstacles associated with controlling superintelligent AI within the next four years.
听
Building a Human-Level Automated Alignment Researcher
听
To achieve their objectives, Sutskever and Leike propose the development of a 鈥渉uman-level automated alignment researcher.鈥� The overarching goal is to leverage AI systems to assist in training other AI systems, enabling them to evaluate and understand alignment challenges. By utilising human feedback, the team aims to train AI systems that can conduct alignment research, ensuring that AI achieves desired outcomes and remains within acceptable boundaries.
听
More from News
- From Workouts To Managing Jetlag: The British Tech Scale-Up That Just Hit One Million Users Globally Appoints New CEO
- Hackers Tricked Instagram鈥檚 AI To Leak Your Log In Details 鈥� How Can Users Stay Protected?
- New Research Reveals The UK鈥檚 Top 10 鈥淔uture-Ready鈥� Cities
- New Research Shows How Elections Are Impacting The Job Market 鈥� Here鈥檚 How
- Is London Becoming The World鈥檚 Next AI Capital?
- Google鈥檚 AI Can鈥檛 Even Spell 鈥淕oogle鈥� 鈥� So Why Is It Replacing Search?
- Will AI Labels Actually Save YouTube From AI Slop?
- The Rise Of 鈥淣ew Brand鈥� Cybercrime Groups And The Business Of Ransomware
听
The Hypothesis of AI Advancement in Alignment Research
OpenAI鈥檚 hypothesis is that AI can make faster progress in alignment research compared to humans. Sutskever, Leike, and their colleagues, John Schulman and Jeffrey Wu, believe that AI systems, working in collaboration with human researchers, can conceive, implement, study, and develop more effective alignment techniques. This symbiotic relationship will allow human researchers to focus on reviewing AI-generated alignment research, rather than generating it themselves.
听
Acknowledging Limitations and Challenges
听
While OpenAI is optimistic about the potential of AI in alignment research, the team acknowledges the inherent risks and limitations involved. They caution that utilising AI for evaluation purposes may amplify inconsistencies, biases, and vulnerabilities within the AI itself. Additionally, they recognise that the most challenging aspects of the alignment problem may extend beyond the realm of engineering.
听
A Collective Effort for the Greater Good
听
Despite the obstacles, Sutskever and Leike believe that the pursuit of superintelligence alignment is crucial. They emphasise the need for machine learning experts, both within and outside of OpenAI, to contribute their expertise in solving this critical challenge. OpenAI鈥檚 commitment extends beyond its own models, as the organisation aims to share its findings widely and actively contribute to the alignment and safety of non-OpenAI AI systems.
听
Looking Ahead
听
OpenAI鈥檚 formation of the Superalignment team demonstrates its commitment to proactively addressing the potential risks associated with superintelligent AI systems. By leveraging the power of AI itself, OpenAI seeks to develop novel strategies to ensure the alignment and control of advanced AI. As the era of superintelligent AI approaches, the work of this team will play a pivotal role in shaping the safe and responsible development of AI technologies for the benefit of humanity.
