Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

Analyzing student votes across AI models for college essay help

studyarena.com

Post reply on HN
Print view View original

81–88 of 88 posts

Re: Analyzing student votes across AI models for college essay help

#81

Post by StableAlkyne »

mobius47 wrote: post #46
StableAlkyne wrote: post #10

Earlier quoted context omitted.

For real, the "Claudish" has become so painful to read that it just takes me out of whatever task I was working on. When prompted to use simple English without jargon, it's still filled with load bearing honest caveats in every footgun seam it talks about — what I should have led with. And I'm not the only one to notice this. Next time it's up for renewal, my team is abandoning it for GH Copilot in order to use liter…

good thing claudish isnt a programming language

The grip isn't part of the hammer, but it's reasonable to replace it if it's uncomfortable to hold and use.

Re: Analyzing student votes across AI models for college essay help

#82

Post by pasharayan »

StableAlkyne wrote: post #80
glimshe wrote: post #69

Earlier quoted context omitted.

That claim about load bearing is doing a lot of work there! I'm curious to know how "Claudish" emerged during the training process. Why each AI has a particular voice if much of the training material is the same across AIs?

They train Claude on its own output and conversations with users, so tics like this are going to get amplified by virtue of being more common in the training set. That, and my conspiracy hat says it's a way of watermarking the output.

NGL i also suspect the particular brand of Anthropic safety filters cut out passionate/fun personality traits

Re: Analyzing student votes across AI models for college essay help

#83

Post by xtiansimon »

pasharayan wrote: post #74
xtiansimon wrote: post #73

> “The best response must be complete without becoming shapeless, structured without sounding mechanical…” Anyone else scratching their head at these descriptions? Uh, your writing is shapeless. You’re 5% too mechanical. Who talks like this? Fiction writers and editors??

TBH :') that one was an AI slip through. In other comments i've flagged the things that were hard rewritten - but even on me that's bad.

Slip from where? Who talks like this putting these semantic concepts into this space? Somebody’s vector, but I don’t recall this in my college education about English composition.

Re: Analyzing student votes across AI models for college essay help

#84

Post by basch »

Aurornis wrote: post #37

The spread isn't as large as I thought from the headline. It's closer to a toss-up than I would have expected. The length of the response is a huge factor: > Students tended to prefer longer responses. The selected answer was 37% longer on average than the alternatives. The longest response won 47.7% of decisive writing comparisons. The shortest still won 25.0%. So the score is partially a proxy for longest responses…

>Makes me wonder how much the reviewers actually read the text.

How many of the college students voting have years of ai use under their belt, where ai voice itself has shaped and influenced their stylistic choices of language preference?

Re: Analyzing student votes across AI models for college essay help

#85

Post by basch »

Aurornis wrote: post #40
avaer wrote: post #19

> How to use Gemini for a college essay Given that this is increasingly the go-to for a college degree, college needs to rethink its cirricula and place in the world. Or at least get rid of the essay. Lest it become a place where student and teacher ais go to play pay-to-win social deduction video games.

My professor and teacher friends are painfully aware of how many students submit AI generated essays. They're adding steps like having the students discuss and defend their essay, which immediately reveals the people who had AI write something and thought they could bluff. This triggers complaints about social anxiety and such, which are unfortunately becoming the go-to defense when unable to discuss the work. They'r…

>They're also moving toward more in-person writing. Instead of long essays, shorter writing segments as part of the test

Why did this ever go away? That was a completely regular part of college a decade plus ago.

Re: Analyzing student votes across AI models for college essay help

#86

Post by crooked-v »

Aurornis wrote: post #37

The spread isn't as large as I thought from the headline. It's closer to a toss-up than I would have expected. The length of the response is a huge factor: > Students tended to prefer longer responses. The selected answer was 37% longer on average than the alternatives. The longest response won 47.7% of decisive writing comparisons. The shortest still won 25.0%. So the score is partially a proxy for longest responses…

Way back when I was in high school, the most important part of essay writing was figuring out how to expand the topic I cared nothing about to the required X pages. I'm unsurprised that college students would default to the same thing.

Re: Analyzing student votes across AI models for college essay help

#88

Post by pasharayan »

crooked-v wrote: post #86
Aurornis wrote: post #37

The spread isn't as large as I thought from the headline. It's closer to a toss-up than I would have expected. The length of the response is a huge factor: > Students tended to prefer longer responses. The selected answer was 37% longer on average than the alternatives. The longest response won 47.7% of decisive writing comparisons. The shortest still won 25.0%. So the score is partially a proxy for longest responses…

Way back when I was in high school, the most important part of essay writing was figuring out how to expand the topic I cared nothing about to the required X pages. I'm unsurprised that college students would default to the same thing.

I think this is one of the most awkward parts of essay writing that AI does help with .. which is filling in the words to fill the word count.
Post reply on HN