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.
Generative models do not guarantee factuality.
Data representation and design can cause unequal or biased behavior.
Data representation and design can cause unequal or biased behavior.
Important decisions still require appropriate oversight.
Important decisions still require appropriate oversight.
Settings, sampling, and inputs can change output behavior.
Settings, sampling, and inputs can change output behavior.
Try it yourself
An example you can run in a temporary verification environment.
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。Expected result
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
- Command output formatting can vary slightly by distribution or tool version.
- Run the example in a temporary directory or process when possible.
Foundation review
Read the scope first
Check whether the command acts on the current shell, a new process, an existing process, or a file.
Verify the observable result
Use the supplied command and compare the output with the expected result.