引導式測驗 · 中等 等級

Magic AI 長上下文程式碼模型測驗

探索 Magic 的 LTM 模型、長上下文檢索、HashHop 評估、程式碼庫推理以及其序列演算法目標的成本問題。

問題 1 的 8

Magic 表示它正在追求什麼軟體開發方向?

預覽每個問題8 問題

當您參加測驗時,就會出現答案和解釋。

  1. Magic 表示它正在追求什麼軟體開發方向?
    • Developing AI models and agents for software-engineering tasks
    • Replacing all software repositories with image datasets
    • Building a spreadsheet-only OCR service
    • Generating code without considering project context
  2. Magic 在 2024 年 8 月為 LTM-2-mini 宣布的最大上下文容量是多少?
    • Up to 100 thousand tokens
    • 最多 1 億個代幣
    • Up to 1 million tokens
    • Up to 10 billion tokens
  3. Magic 使用 HashHop 來評估什麼?
    • How well a model predicts a familiar fact from pretraining
    • Whether generated source code passes every production test
    • Retrieval and chaining over random hash pairs placed in a supplied long context
    • How quickly a model compiles a new programming language
  4. 為什麼 Naive Transformer Attention 對於 1 億個 token 的上下文來說是一個問題?
    • 不花錢
    • 它只能離線工作
    • 它刪除輸入
    • 它隨序列長度呈二次方擴展,變得極為昂貴
  5. 2024 年 Magic 與哪家公司合作建造超級電腦?
    • Google 雲
    • Apple
    • Spotify
    • Adobe
  6. What does a larger context window make possible for a coding task?
    • 鍵盤打字速度更快
    • Include more cross-file code and documentation in one context, without guaranteeing project-wide correctness
    • 更好的螢幕分辨率
    • 電費更便宜
  7. What comparison did Magic report for LTM-2-mini’s sequence-dimension algorithm?
    • A 1,000-fold improvement in total cost for every deployed model
    • A 1,000-fold increase in the accuracy of all code edits
    • About 1,000 times lower per-token algorithmic cost than Llama 3.1 405B attention at 100M context in the reported configuration
    • A fixed 1,000-token limit for every LTM model
  8. In a simple illustrative lookup with A → B, B → C, and C → D, what chain follows from A?
    • A → C → B → D
    • A → B → D → C
    • A → D → C → B
    • A → B → C → D