Loading page...Загружаем страницу...正在加载页面...
AtlasRepo

I Spent 1 Billion Tokens Making a Real Chip with AI — and Found Its True Limits

说明与用途

两名 AI 代理和一名人类共同完成了 SHA‑256 加速器的设计与 SoC 集成,耗费 10 亿个 token,完成 10 项签核。项目揭示了 AI 的局限,并提出四条验证规则以防止过早完成。

问题

Designing a functional SHA‑256 accelerator and integrating it into a SoC using AI agents incurred a huge token cost and exposed limits of LLMs in complex engineering workflows.

结果

The AI‑driven workflow produced a fully sign‑off‑grade SHA‑256 core and its integration into a 1.2 M‑unit SoC, demonstrating that LLMs can handle complex engineering tasks when coupled with rigorous verification mechanisms.

工作流

  • 1. Planner AI (deepseek‑v4‑pro) drafted a design plan and strategy.
  • 2. Executor AI (GLM‑5.3) ran EDA tools, produced reports, and executed the plan step‑by‑step.
  • 3. Human reviewer made judgment calls, broke ties, and performed final sign‑off.
  • 4. Dual‑agent independent review ensured executor evidence was re‑audited by planner.
  • 5. Three‑layer verification checked final results, cross‑checked numbers, and sanity‑checked plausibility.
  • 6. Claim‑vs‑evidence tables recorded each claim and verified against raw logs.
  • 7. Honest scope control prevented premature acceptance of incomplete designs.

证据

10 signoff checks, all green. This is the headline — an LLM agent can reach signoff‑grade, not just "generate a plausible Verilog."

来源

AI’s biggest danger is not that it can’t do the work. It’s that it stops early and tells you it’s done — with full confidence.

来源

Dual‑agent, independent review: Never let AI be both player and referee.

来源

  • 记录日期: 2026-09-06T05:38:00.505Z