- Quilter’s AI built a dual-PCB Linux computer in just a week
- The system booted Debian on the first try with minimal human help.
- Engineers spent just 38.5 hours, while AI completed most of the design.
Los Angeles-based startup Quilter has unveiled Project Speedrun, a Linux computer built entirely with artificial intelligence assistance.
The machine includes 843 components on dual PCBs and the team designed and assembled it in just one week.
Surprisingly, the computer booted Debian on its first attempt and required only 38.5 hours of human intervention.
Training for precision, not imitation
The performance of this device is in stark contrast to traditional workflows, which typically require approximately three months of expert human labor to complete a similar project.
AI handled the iterative design, execution, and cleanup phases that typically hinder engineers’ creativity and delay development timelines.
Quilter trained his AI differently than large language models like GPT-5 or Claude.
Instead of studying human-designed boards, which often include errors, the system learned by optimizing the physical laws that govern circuit design.
This approach prevented human limitations from limiting their capabilities.
By focusing on physics-based optimization rather than imitation, AI proposed novel component designs and arrangements.
In theory, it outperforms human designers in efficiency and innovation, although engineers still oversee the process.
His role became one of supervision and creative refinement rather than repetitive execution.
By eliminating manual bottlenecks, engineers can iterate faster and explore more experimental designs.
The traditional three-step setup, run, and cleanup workflow often introduces errors during execution, which then require further human correction.
Quilter’s AI eliminates much of this friction, allowing smaller teams to complete complex workstation designs in a fraction of the usual time.
The result is a project that offers a fully functional system while reducing human workload, which could reduce barriers for startups creating custom mobile workstations and mini PCs.
Quilter CEO Sergiy Nesterenko envisions a future where AI designs not only match those of human engineers, but can also “generate better designs for circuit boards than humans have ever attempted to make.”
Although Quilter’s approach could accelerate innovation, its long-term reliability in more complex systems has not yet been proven.
Through Tom Hardware
Follow TechRadar on Google News and add us as a preferred source to receive news, reviews and opinions from our experts in your feeds. Be sure to click the Follow button!
And of course you can also follow TechRadar on TikTok for news, reviews, unboxings in video form and receive regular updates from us on WhatsApp also.
