Kuis terkait panduan · Sedang Tingkat

Kuis Model Kode Konteks Panjang AI Ajaib

Jelajahi model LTM Magic, pengambilan konteks panjang, evaluasi HashHop, alasan basis kode, dan masalah biaya yang menjadi target algoritme urutannya.

Jalur panduan terkaitModel Kode Konteks Panjang AI Ajaib
Pertanyaan 1 dari 8

What software-development direction has Magic said it is pursuing?

Pratinjau setiap pertanyaan8 pertanyaan

Jawaban dan penjelasan muncul saat Anda mengikuti kuis.

  1. What software-development direction has Magic said it is pursuing?
    • 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. What maximum context capacity did Magic announce for LTM-2-mini in August 2024?
    • Up to 100 thousand tokens
    • Hingga 100 juta token
    • Up to 1 million tokens
    • Up to 10 billion tokens
  3. What does Magic use HashHop to evaluate?
    • 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. Mengapa perhatian transformator yang naif menjadi masalah dalam konteks 100 juta token?
    • Tidak ada biaya apa pun
    • Ini hanya berfungsi offline
    • Ini menghapus masukan
    • Ini berskala kuadrat dengan panjang urutan, menjadi sangat mahal
  5. Perusahaan manakah yang bermitra dengan Magic pada tahun 2024 untuk membangun superkomputer?
    • Google Awan
    • Apple
    • Spotify
    • Adobe
  6. What does a larger context window make possible for a coding task?
    • Mengetik lebih cepat di keyboard
    • Include more cross-file code and documentation in one context, without guaranteeing project-wide correctness
    • Resolusi layar lebih baik
    • Tagihan listrik lebih murah
  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