神经计算机

摘要

我们提出一个新前沿：神经计算机（NCs）——一种新兴的机器形态，它将计算、内存和输入/输出统一于学习生成的运行时状态中。与传统计算机执行显式程序、智能体在外部执行环境中行动、世界模型学习环境动力学不同，NCs致力于让模型自身成为运行的计算机。我们的长期目标是实现完全神经计算机（CNC）：这一新兴机器形态的成熟通用版本，具备稳定执行、显式重编程和可持续能力复用的特性。作为初步探索，我们研究早期NC基元是否能仅从采集的I/O轨迹中学习获得，而无需插桩程序状态。具体而言，我们将NC实例化为视频模型，在命令行和图形界面设置中根据指令、像素和用户操作（若可用）推演屏幕帧序列。这些实现表明，学习型运行时可以掌握早期交互基元，特别是I/O对齐和短时程控制，但常规复用、受控更新和符号稳定性仍是待解难题。我们围绕这些挑战规划了通往CNC的路线图。若能突破这些障碍，CNC有望建立超越现有智能体、世界模型和传统计算机的新型计算范式。

English

We propose a new frontier: Neural Computers (NCs) -- an emerging machine form that unifies computation, memory, and I/O in a learned runtime state. Unlike conventional computers, which execute explicit programs, agents, which act over external execution environments, and world models, which learn environment dynamics, NCs aim to make the model itself the running computer. Our long-term goal is the Completely Neural Computer (CNC): the mature, general-purpose realization of this emerging machine form, with stable execution, explicit reprogramming, and durable capability reuse. As an initial step, we study whether early NC primitives can be learned solely from collected I/O traces, without instrumented program state. Concretely, we instantiate NCs as video models that roll out screen frames from instructions, pixels, and user actions (when available) in CLI and GUI settings. These implementations show that learned runtimes can acquire early interface primitives, especially I/O alignment and short-horizon control, while routine reuse, controlled updates, and symbolic stability remain open. We outline a roadmap toward CNCs around these challenges. If overcome, CNCs could establish a new computing paradigm beyond today's agents, world models, and conventional computers.