Guide-yakabatana mibvunzo · Zvakaoma Nhanho
Maitiro ekuve AI Injiniya Quiz
Inoedza iyo AI injinjini yekudzidza nzira, maitiro ekudzoreredza-akawedzera chizvarwa mapaipi anoshanda, uye nei kuongorora kudzoreredza uye chizvarwa zvine basa.
Mubvunzo 1 ye 8
Kutariswa kweinjiniya yeAI kwakasiyana sei kubva kumuchina wekudzidza mainjiniya, maererano negwaro?
Tarisa mubvunzo wese8 mibvunzo
Mhinduro uye tsananguro zvinoonekwa paunenge uchitora bvunzo.
- Kutariswa kweinjiniya yeAI kwakasiyana sei kubva kumuchina wekudzidza mainjiniya, maererano negwaro?
- AI engineers design GPUs, while ML engineers write prompts
- AI engineers build applications on top of existing foundation models, while ML engineers train and deploy models
- AI engineers only do data analysis and statistics
- There is no difference between the two roles
- Sei gwara richikurudzira kudzidza mbishi LLM APIs pamberi pemafuremu seLangChain?
- Frameworks are illegal to use commercially
- Raw APIs are always faster to write
- Frameworks cannot call LLMs
- It makes debugging any framework much easier later
- Chii chinonzi Model Context Protocol?
- An open standard for connecting models to tools and data
- A law regulating AI engineers
- Nzira yekumanikidza modhi maremu
- A benchmark for measuring model accuracy
- Mune pombi yeRAG, chii chinoitika panguva yekunwa?
- The model is retrained on each user question
- Users rate answers from one to five stars
- Documents are chunked, embedded and stored with metadata
- The system deletes old documents every day
- Sei sisitimu ichimhanyisa BM25 kiyi yekutsvaga padivi pekutsvaga kwevector?
- To catch exact keyword matches such as names and codes that embeddings may miss
- Because vector search cannot return more than one result
- To avoid storing any metadata
- Because BM25 generates the final answer text
- What does recall at k measure in RAG evaluation?
- How quickly the model generates each token
- Whether the correct chunk appears among the top k retrieved results
- How many users return to the app after k days
- The number of words in the final answer
- According to the guide, where do many wrong RAG answers trace back to?
- The user's internet connection
- The model's temperature setting always being too low
- The programming language used
- Retrieval failures rather than the model itself
- Which misconception does the guide correct about starting in AI engineering?
- That solid software engineering matters
- That evaluations help catch regressions
- That you need a PhD or advanced mathematics to begin
- That prompt injection is a security concern