Hacker News Reader

Comment by resiros | Hacker News Reader

Not sure I agree with the AI edited comments. Using AI to improve the readability and clarity is fine. Sometimes a well structured comment is much better than a braindump that reads like ramblings. And AI is quite good at it (and probably will get better). To make the point, here is how this comment would have looked if edited:

"I don't fully agree with banning AI-edited comments. Using AI to improve readability and clarity is a reasonable thing to do. A well-structured comment is often much better than a braindump that reads like rambling. AI is quite good at this, and it will probably get better. To illustrate the point, here is how this comment would have looked if edited"

View on HN

I prefer your non-edited version. My brain automatically starts to zone out with the AI edited version, side effect of having read way too much AI text

I also prefer the original version - the AI version has a strange vibe.

Not to take away from your point, but I like your original one better.

Non-edited is better. It flows and reads faster. The AI sentences they feel clinical and sterile. They feel, well, like AI.

I had never noticed the flow of AI text. They do make the flow of reading feel weird with a lot of pauses! Thanks for pointing it out

The edited version is an example of a sterile/canned response. No one talks like that.

While I do edit my comments to fix typos, certain spelling oddities and other peculiarities would be present.

It's a matter of taste, but your original writing is way better. Your writing has your voice. Like dropping the "I am" from your first sentence, using parentheticals, couching your point in understatement (e.g "sometimes" meaning often instead of just saying "often").

The AI comment might be clear, but it sounds like a press release, not a person, and there's nothing to engage with.

For all the people saying they prefer the non-edited version: would y'all be saying that if you didn't already know which one was the non-edited version? Be honest.

There's nothing inherently better about the edited version. It's just saying the same thing with synonyms substituted, at a slightly more formal but less personal register. HN comments are not academic text, colloquial turns of phrase are perfectly fine and expected.

> There's nothing inherently better about the edited version.

Easier to read ==> More likely to be read.

No, it's not saying the same thing, especially if the tool is telling you that your statement is ambiguous and should be rephrased.

More formal register doesn’t mean easier to read or understand. To many people the exact opposite is the case.

> More formal register doesn’t mean easier to read or understand.

And who is advocating for a more formal register?

Easier to read is mostly related with predictability of the text. Any time the brain mispredicts the next word, you'd have to go back and re-read.

Unless you are purposely train on that specific way to expression, it ain't easier to read.

I don't know why this is confusing. If I forget to put the "not" qualifier in a sentence, do we agree that it can confuse (or worse, mislead) the reader?

I never said - confusing. Just not easier to read as in relative term.

I don't think the edited version is easier to read.

I'll ask the same question I asked someone else:

https://news.ycombinator.com/item?id=47342324

You're saying removing ambiguity does not make it easier to read? You're saying using a word that means nothing like what you meant to say is easier to read than using the correct word?

Really?

What are you referring to? What word did the GP use that means nothing like what they meant to say?

OK. My brain farted, and I misunderstood the top post to be saying something else, and your and others' criticisms were misinterpreted by me.

Now here's the thing. I wrote all my prior comments on a machine with no LLM access. On my personal machine, I had a while ago installed a TamperMonkey script that sends my draft, along with all the parents (to the root) to an LLM for feedback (with a specific prompt). All it does is give feedback (logical errors, etc). So I tried again with one of my comments, and its feedback found several flaws with my comment, and ended it with this suggestion:

"Considering all this, it might be BETTER to either not reply ..."

Had I had this advice when I was writing those comments, it would have saved me and others a fair amount of time.

This is (mildly) useful. It'd be sad to ban such use.

Reply on news.ycombinator.com