Introduce generative AI to an internal workflow.
Explain limitations so users do not over-trust it.
Choose two common limitations.
Generative AI can hallucinate and can reflect bias in data; human review and evaluation remain necessary.
Detailed explanation
Generative models do not guarantee factuality.
Data representation and design can cause unequal or biased behavior.
Important decisions still require appropriate oversight.
Settings, sampling, and inputs can change output behavior.
Check official documentation
Compare the following points with the official documentation.
AWS公式AIF-C01ガイドDomain 2.1の生成AIの限界と責任ある利用を確認する。
Official references
What to confirm
事実性と偏りの限界を挙げ、検証や人間の監督が必要だと説明できる。
Key points
- Hallucination
- Bias
- Human review
Notes
- Environment: AWS公式AIF-C01試験ガイドとAWS公式ドキュメントの確認
- Compare the definition with the AIF-C01 objective and the service documentation before applying it.
- Keep the concept separate from a particular answer choice or implementation step.
Foundation review
Plausibility versus truth
Fluent wording does not establish that a generated claim is factually supported.
Data influence
Training and input data can affect which groups, cases, or viewpoints a system serves well.