跳到正文
𝕏 Rohan Paul(x.com)·· 7 天前品質評分57
重點導讀

晶片模擬會留下大量訊號變化紀錄,檔案可能超過 10 GB,工程師得自己翻找,AI 助理也無法一次讀完。

  • Google DeepMind 與 Columbia University 的研究團隊做出 BTTF,把紀錄整理成 SQLite 資料庫,再讓 AI 助理把白話問題轉成 SQL 查詢、檢查設計規則並核對答案。在 150 題專家標記的驗證題中,使用 Gemini 2.5 Pro 答對 95.33%。
  • 多個 AI 助理分工的品質稽核分數比單一 AI 助理高 17.3%,但延遲也增加到 1.96 倍。這種做法能讓大型紀錄更容易查詢,也呈現了答題品質與速度之間的取捨。

AI 伴隨問答

自備 Key 深度分析

針對這篇報導有疑問?可直接點選快捷問題或向 AI 追問背景脈絡與技術細節:

Rohan Paul
Rohan Paul@rohanpaul_ai
·7 天前
𝕏

Google DeepMind and Columbia Univ paper argues that AI agents can debug chip simulations once the huge waveform files become a SQL database they can query.

Chip simulations record every signal change, and these dumps can exceed 10 GB of text that engineers still scan by hand. No LLM context can hold that, and the files offer no way for an agent to search them.

They built Back-to-the-Future (BTTF), which converts the dumps into a compact SQLite database. A team of agents then turns plain-English questions into SQL, checks design rules, and audits each answer.

On 150 expert-labeled verification questions, it answered 95.33% correctly using Gemini 2.5 Pro. Splitting the work across specialized agents scored 17.3% higher on a quality audit than 1 agent alone, at 1.96x the latency.

If your agents struggle with huge logs or traces, put the data in a queryable database instead of pushing it into the prompt.

推文來源 · X (Twitter)在 X 參與討論

讀者討論

理性交流 · 即時討論