An AI computing enthusiast, Angel (@Angaisb_), successfully demonstrated the classic game Doom running on a custom CPU. This CPU, dubbed 'Codex-R32', was designed by the AI model GPT-5.6 Sol. The demonstration took place within the sandbox environment of the game Turing Complete.
The 'Codex-R32' CPU was constructed from primitive logic components available within Turing Complete. The Doom implementation used the C-based PureDOOM port, which was compiled into native RV32IM machine code to run directly on the custom AI-designed CPU. The performance was not described as playable, but the functionality was confirmed.
The demonstration included a video showing the game's viewport overlaid on a pulsing schematic of the custom CPU. This schematic provided a live visualization of processor gates, registers, memory, and ALUs, along with live statistics such as cycle counter, simulation speed, and memory/register values, all within the Turing Complete environment.
This achievement highlights the capability of large language models like GPT-5.6 Sol to not only generate software but also to design functional virtual hardware. The successful execution of Doom, a common benchmark for computing capabilities, suggests a notable step in AI's ability to create complex system architectures.
✨ This summary was generated by AI from the outlets' reporting listed below. It is not independently verified and may contain errors — check the original sources. How BrevFeed works →
One email each morning: the day's tech stories, clustered across outlets and summarized. No account needed.
One email a day. Unsubscribe in one click, any time.
Spend a few minutes, get the whole day. Every topic's top stories in one hands-free rundown — listen, watch, or read the transcript.
▶ Play today's briefNew every morning, and the back catalogue is archived by date.
An AI computing enthusiast demonstrated Doom running on a custom CPU named 'Codex-R32' designed by GPT-5.6 Sol within the Turing Complete game environment. This showcases the AI's capability to construct functional virtual hardware from basic logic components, indicating advancements in AI-driven hardware design.