Although some current AIs surpass human abilities especially in closed artificial worlds such as board games, their abilities in the real world are limited. They make strange mistakes and do not notice them. They cannot be instructed easily, fail to use common sense, and lack curiosity. They do not make good collaborators. Mainstream approaches for creating AIs are built using the traditional manually-constructed symbolic AI approach and generative and deep learning AI approaches including large language models (LLMs). These systems are not well suited for creating robust and trustworthy AIs. Although it is outside of the mainstream, the developmental bootstrapping approach has more promise. In developmental bootstrapping, AIs develop competences like human children do. They start with innate competences. They interact with the environment and learn from their interactions. They incrementally extend their innate competences with self-developed competences. They interact and learn from people and establish perceptual, cognitive, and common grounding. They acquire the competences that they need through an incremental bootstrapping process. However, developmental robotics has not yet produced AIs with robust adult-level competences. Projects have typically stopped at the Toddler Barrier corresponding to human infant development at about two years of age, before their speech is fluent. They also do not bridge the Reading Barrier, to skillfully and skeptically tap into the vast socially developed recorded information resources that power LLMs. The next competences in human cognitive development involve intrinsic motivation, imitation learning, imagination, coordination, and communication. This position paper lays out the logic, prospects, gaps, and challenges for extending the practice of developmental bootstrapping to acquire further competences and create robust and resilient AIs.

翻译：尽管当前部分人工智能在封闭人工环境（如棋盘游戏）中已超越人类能力，但其在现实世界中的表现仍十分有限。它们会犯下异常错误且无法察觉，难以通过简单指令进行引导，缺乏常识认知与好奇心，更无法成为优秀的协作伙伴。创建人工智能的主流方法包括传统人工构建的符号主义人工智能范式，以及生成式与深度学习（含大型语言模型）等方法。这些系统并不适用于构建稳健可信的人工智能。虽然发展性自举方法并非主流路径，却展现出更大潜力。在发展性自举中，人工智能像人类儿童一样逐步发展能力：它们从先天能力出发，通过与环境互动进行学习，在先天能力基础上渐进式构建自生能力，在与人类互动中建立知觉、认知与常识根基，最终通过渐进式自举过程获取所需能力。然而，发展机器人学尚未培育出具备人类成年级稳健能力的人工智能。研究项目通常止步于"幼儿屏障"——对应约两岁人类婴幼儿阶段（流畅语言形成前），且未能跨越"阅读屏障"——即无法熟练且批判性地利用支撑大型语言模型的海量社会性记录信息。人类认知发展的后续能力涉及内在动机、模仿学习、想象力、协调与沟通。本立场文件阐述了通过扩展发展性自举实践以获取更高阶能力、构建稳健韧性人工智能的逻辑框架、发展前景、现存差距与核心挑战。