logoalt Hacker News

ilakshyesterday at 7:33 PM1 replyview on HN

They were using Sonnet 4.6 for some fre form responses so that could be applied to something subjective.


Replies

boulosyesterday at 8:46 PM

But it's not clear that using Sonnet or any other LLM as a "grader" would result in the same improvement. For objective grading, you could be sure that the additional adaptive support is helping. For subjective things like writing style, literature, poetry, you end up with whatever Sonnet thinks is good (and randomly so).

It still could be better for students, but it's not obvious that it would be (or maybe not as strongly?).