Magic AI Long-Context Code Models Quiz

Answers and explanations appear as you take the quiz.

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
   • Up to 100 million tokens
   • 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. Why is naive transformer attention a problem for 100-million-token contexts?
   • It costs nothing
   • It only works offline
   • It deletes the input
   • It scales quadratically with sequence length, becoming prohibitively expensive
5. Which company did Magic partner with in 2024 to build supercomputers?
   • Google Cloud
   • Apple
   • Spotify
   • Adobe
6. What does a larger context window make possible for a coding task?
   • Faster typing on a keyboard
   • Include more cross-file code and documentation in one context, without guaranteeing project-wide correctness
   • Better screen resolution
   • Cheaper electricity bills
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