recursive self-improvement
Recursive self-improvement is a cycle in which an AI system improves itself and each improved version improves itself further.
Recursive self-improvement describes a process in which an AI system improves its own design or training, and the improved system then carries out the next round of improvement. Because capabilities could grow rapidly with each cycle, the idea is often discussed alongside the concept of an intelligence explosion.
In AI safety, it is treated as a major risk factor because capabilities could grow faster than humans can understand or oversee. It is frequently raised in connection with the automation of AI research by AI systems.
This entry is based on AIPOST articles and widely known facts. If something is wrong, please send us a correction request.
Articles covering this entry
His reasoning is that coding models reached a tipping point late last year, making recursive self-improvement, AI helping to build better AI, a reality.
One concern is recursive self-improvement: an AI system gaining the ability to change itself or help create more capable successors, accelerating the cycle.