AWS Certified AI Practitioner417 questions across 42 pages are complete and free, with no account or card.
417 questions in this bank
Free access · progress saved on this device
Which option is a benefit of ongoing pre-training when fine-tuning a foundation model (FM)?
Answer: B
The correct answer is B. Ongoing pre-training improves model performance over time by allowing the model to adapt to new data and tasks.
Source: Adapted from community discussion — may2021_r
What are tokens in the context of generative AI models?
Answer: A
In the context of generative AI models, tokens are the smallest units of text that the model processes. A token could represent an entire word, a subword, or even a single character, depending on how the model is tokenized. Tokens are the basic building blocks for both input and output in natural language processing (NLP) tasks, such as text generation or translation.
Source: Adapted from community discussion — Jessiii
A company wants to assess the costs that are associated with using a large language model (LLM) to generate inferences. The company wants to use Amazon Bedrock to build generative AI applications. Which factor will drive the inference costs?
Answer: A
A. Number of tokens consumed. More tokens used = higher cost. All other affects training costs, not inference costs. Correct answer is A
Source: Adapted from community discussion — OnePG
A company is using Amazon SageMaker Studio notebooks to build and train ML models. The company stores the data in an Amazon S3 bucket. The company needs to manage the flow of data from Amazon S3 to SageMaker Studio notebooks. Which solution will meet this requirement?
Answer: C
A company has a foundation model (FM) that was customized by using Amazon Bedrock to answer customer queries about products. The company wants to validate the model's responses to new types of queries. The company needs to upload a new dataset that Amazon Bedrock can use for validation. Which AWS service meets these requirements?
Answer: A
Which prompting attack directly exposes the configured behavior of a large language model (LLM)?
Answer: D
D: Extracting the prompt template Explanation: Extracting the prompt template is a prompting attack where an attacker intentionally crafts inputs to reveal the underlying configuration or instructions (prompt template) used to guide the large language model (LLM). This exposes the internal behavior or design of the model, potentially revealing sensitive or proprietary information about how the LLM is configured. Why not the other options? A: Prompted persona switches: This attack involves manipulating the LLM to adopt a different persona or role than intended but does not directly expose the prompt template.
Source: Adapted from community discussion — Moon
A company wants to use Amazon Bedrock. The company needs to review which security aspects the company is responsible for when using Amazon Bedrock. Which security aspect will the company be responsible for?
Answer: C
C. Securing the company's data in transit and at rest Explanation: When using Amazon Bedrock, the company is responsible for securing its data both in transit and at rest. This involves ensuring the confidentiality and integrity of the data that is uploaded to Amazon Bedrock or transmitted to and from the service.
Source: Adapted from community discussion — aws_Tamilan
A social media company wants to use a large language model (LLM) to summarize messages. The company has chosen a few LLMs that are available on Amazon SageMaker JumpStart. The company wants to compare the generated output toxicity of these models. Which strategy gives the company the ability to evaluate the LLMs with the LEAST operational overhead?
Answer: B
A company is testing the security of a foundation model (FM). During testing, the company wants to get around the safety features and make harmful content. Which security technique is this an example of?
Answer: D
D. Jailbreak Explanation: Jailbreaking is a technique used to bypass the safety features and restrictions of a foundation model (FM). The goal is to manipulate the model into generating harmful, inappropriate, or otherwise unintended content, despite the safeguards in place. This is often done to test the robustness of the model's safety mechanisms.
Source: Adapted from community discussion — aws_Tamilan
A company wants to create a chatbot by using a foundation model (FM) on Amazon Bedrock. The FM needs to access encrypted data that is stored in an Amazon S3 bucket. The data is encrypted with Amazon S3 managed keys (SSE-S3). The FM encounters a failure when attempting to access the S3 bucket data. Which solution will meet these requirements?
Answer: A
A: Ensure that the role that Amazon Bedrock assumes has permission to decrypt data with the correct encryption key. Explanation: When data in an Amazon S3 bucket is encrypted using SSE-S3 (Server-Side Encryption with Amazon S3 managed keys), the IAM role used by the application (in this case, Amazon Bedrock) must have permissions to access and decrypt the data. Assigning the correct permissions to the role ensures that the Foundation Model (FM) can access the encrypted data.
Source: Adapted from community discussion — Moon
Keyboard:J Kmove between questionsA–Dselect an answerRshow or hide the answer← →change page
AIF-C01 practice, question 131. 417 questions available.
Version 1.0.0. How we source questions