AI Agent Designs a RISC-V CPU Core From Scratch
TL;DR
In 2020 researchers fine-tuned a GPT-2 model to design fragments of logic circuits; in 2023 researchers used GPT-4 to help design an 8-bit processor with a novel instruction set; by 2024, a variety of LLMs could design and test chips with basic functionality, like dice rolls (though often these were flawed). Now Verkor.io, an AI chip design start-up, claims a bigger milestone: a RISC-V CPU core designed entirely by an agentic AI system. The CPU, dubbed VerCore, has a clock speed of 1.5 gigahertz and performance similar to a 2011-era laptop CPU. Suresh Krishna, co-founder at Verkor.io, says the team’s key claim is that this approach is more effective than using only specialized AI systems for specialized tasks within the overall design process. “ What we learned is that the better approach is to let the AI agent solve the whole problem,” he says. Bringing human workflows to agentic AI Ver.
Nauti's Take
Verkor. io claiming a fully AI-designed RISC-V core is a genuine milestone — the solve-the-whole-problem approach marks a real leap beyond task-specific AI tools.
At 1.5 GHz with 2011-era performance, VerCore is a benchmark, not a production-ready chip. Hardware design teams should watch closely: this is not a replacement for expert engineers, but a strong signal for how exploratory design workflows may evolve.
Summary
In 2020 researchers fine-tuned a GPT-2 model to design fragments of logic circuits; in 2023 researchers used GPT-4 to help design an 8-bit processor with a novel instruction set; by 2024, a variety of LLMs could design and test chips with basic functionality, like dice rolls (though often these were flawed). Now Verkor.
io, an AI chip design start-up, claims a bigger milestone: a RISC-V CPU core designed entirely by an agentic AI system. The CPU, dubbed VerCore, has a clock speed of 1.5 gigahertz and performance similar to a 2011-era laptop CPU.
Suresh Krishna, co-founder at Verkor. io, says the team’s key claim is that this approach is more effective than using only specialized AI systems for specialized tasks within the overall design process.
“ What we learned is that the better approach is to let the AI agent solve the whole problem,” he says. Bringing human workflows to agentic AI Ver
Sources