Boundless Socratic Learning with Language Games
This is a foundational position paper proposing a theoretical framework for boundless learning in AI, which could impact all of ML/AI if realized.
The paper argues that an agent can master any capability given sufficient feedback, data coverage, and resources, focusing on language agents to propose that recursive self-improvement can vastly exceed initial data limits, constrained only by time and alignment issues.
An agent trained within a closed system can master any desired capability, as long as the following three conditions hold: (a) it receives sufficiently informative and aligned feedback, (b) its coverage of experience/data is broad enough, and (c) it has sufficient capacity and resource. In this position paper, we justify these conditions, and consider what limitations arise from (a) and (b) in closed systems, when assuming that (c) is not a bottleneck. Considering the special case of agents with matching input and output spaces (namely, language), we argue that such pure recursive self-improvement, dubbed "Socratic learning", can boost performance vastly beyond what is present in its initial data or knowledge, and is only limited by time, as well as gradual misalignment concerns. Furthermore, we propose a constructive framework to implement it, based on the notion of language games.