Microsoft GH-300 Exam - Topic 2 Question 1 Discussion

Actual exam question for Microsoft's GH-300 exam

Question #: 1
Topic #: 2

What types of prompts or code snippets might be flagged by the GitHub Copilot toxicity filter? (Each correct answer presents part of the solution. Choose two.)

AHate speech or discriminatory language (e.g., racial slurs, offensive stereotypes)

BSexually suggestive or explicit content

CCode that contains logical errors or produces unexpected results

DCode comments containing strong opinions or criticisms

Show Suggested Answer

Suggested Answer: A, B

GitHub Copilot includes a toxicity filter to prevent the generation of harmful or inappropriate content. This filter flags prompts or code snippets that contain hate speech, discriminatory language, or sexually suggestive or explicit content. This ensures a safe and respectful coding environment.

by Rosenda at Aug 17, 2025, 03:06 PM

Limited Time Offer

25%

Off

Get Premium GH-300 Questions as Interactive Web-Based Practice Test or PDF

Contribute your Thoughts:

Submit Cancel

Cary

4 months ago

I’m surprised they would filter out comments, isn’t that part of coding?

upvoted 0 times

...

Micaela

4 months ago

Wait, C? That doesn't seem right, logical errors aren't toxic!

upvoted 0 times

...

Letha

4 months ago

I think D could also be flagged, strong opinions can be toxic.

upvoted 0 times

...

Viola

4 months ago

A and B for sure, can't believe they even need a filter for that.

upvoted 0 times

...

James

4 months ago

Definitely A and B, those are obvious.

upvoted 0 times

...

Svetlana

5 months ago

I’m a bit confused about option C. Logical errors don’t seem toxic to me, but I guess they could lead to unexpected results that might be flagged?

upvoted 0 times

...

Hannah

5 months ago

I remember practicing with a similar question, and I think A and B were the clear choices. Discriminatory language is a big no-no!

upvoted 0 times

...

Arminda

5 months ago

I'm not entirely sure, but I feel like option D could also be a possibility. Strong opinions in comments might be seen as toxic, right?

upvoted 0 times

...

Graciela

5 months ago

I think options A and B are definitely the ones that would be flagged. We talked about hate speech and explicit content in our last session.

upvoted 0 times

...

Paris

5 months ago

Hmm, this is a tricky one. I'd say A and B for sure, but C and D are a bit more iffy. I suppose the filter might catch some really buggy code or overly opinionated comments, but it's hard to say for sure. Gonna have to think this through.

upvoted 0 times

...

Justine

6 months ago

Okay, let's see. A and B are obvious, but I'm not sure about the other options. I feel like D could also be flagged if the comments are really strong or controversial. Gotta be careful with that.

upvoted 0 times

...

Jina

6 months ago

Oof, I'm not sure about this one. I guess A and B are probably the right answers, but I'm not totally sure what kind of code snippets the filter would catch. Guess I'll have to think it through carefully.

upvoted 0 times

...

Hermila

6 months ago

Hmm, this seems pretty straightforward. I'm pretty confident that A and B are the correct answers - GitHub's toxicity filter would definitely flag hate speech and sexually explicit content.

upvoted 0 times

...