Comment by RealityVoid

3 days ago

I think using AI for a bit more potent spellchecking or style hints is... fine, honestly. I don't usually do it, you can tell from all the silly spelling mistakes I do. But a bit more polishing for your posts is a good thing, not a bad one, as long as it doesn't hide your voice.

The problem is it always hides your voice. Always

  • There is a big difference between "asking an editor for suggestions" and "vibe posting".

    You don't lose your voice if you ask for advice and manually incorporate the suggestions you agree with.

    You might lose your voice if you say "Improve my comment to make it better" and copy-paste the result without another thought.

    • There is theoretically a big difference, but in practice, I think that peopel using AI to 'get suggestions' tend to dramatically under-estimate its impact on their writing.

      It might feel like just a couple of tweaks, but they add up fast.

      2 replies →

  • It hides your voice, and shortcuts your thinking process, because your editing is when you actually evaluate what you think!

    When using LLMs to write, the temptation to avoid actually thinking about what you're communicating is too much for most people.

    • I'm increasingly convinced that most people spend most of their lives actively trying to find ways to avoid actually thinking about things. When I look at it that way I figure that either we achieve benevolent AGI in the near to medium term or society collapses due to whatever the asymptotic form of today's LLMs is.

  • In the words of the comment: the rough edges are what make you.. you!

    Keep polishing and everything eventually turns into a smooth shiny ball. We need texture, roughness, edges.

  • An LLM telling me I mispeled a word isn't changing my voice. Especially when I know the proper spelling and simply have a typo.

    An LLM telling me I omitted a qualifier and that my statement isn't saying what I meant it to say isn't changing my voice - it's ensuring what you see is my voice.

    • There's a simple solution to the spelling part. Use a spell checker. They seem to work pretty well.

  • Yep. I actually prefer seeing imperfect writing, there is signal there that AI would erase.

  • Maybe. But it can also help people find their voice. And I'd rather have comments from someone knowledgeable but unrefined with some good guidance than their silence on that same topic.

  • I had a README with a curse word in it and the agent would try repeatedly to remove it in drive by edits bundle in with some other change.

When do you need to spellcheck or polish an HN comment?

I've never, ever, ever ever ever, seen anybody complain about spelling mistakes in a comment here. As long as you can understand the comment, people respond to it.

  • Extend spellcheck to asking questions like "does it meet HN rules" "how can I improve my writing" etc. Though these are the kinds of questions that do at very least still meet the spirit of the rule, I suppose.

    • Do you really need an automated tool to tell you whether you're breaking common sense guidelines?

      And why would you want to "improve your writing" for an HN comment? I think people here value raw authenticity more than polished writing.

      9 replies →

  • People who are particular about spelling do not want to write misspelled words! It's not about whether you/others will tolerate it. I have my standards, and I hold to them.

    I personally don't use an LLM to spellcheck (browser spellcheck works fine), but I see no problem with someone using an LLM to point out spelling errors.

    And while I don't complain about others' spelling errors, I sure do notice them. And if someone writes a long wall of text as one giant paragraph that has lots of spelling/grammatical issues, chances are very high I won't read it.

    Some people write very poorly by almost any standard. If an LLM helps the person write better, I'm all for it. There's a world of a difference between copy/pasting from the LLM and asking it for feedback.

    • > I have my standards, and I hold to them.

      Spellcheckers exist, you don't need an AI to change your voice.

      Also, if you have standards, you can always train yourself to spell better!

      4 replies →

  • I think that people subconsciously perceive grammatically correct and stylistically appropriate writing as more authoritative. And author is perceived as smarter and/or better educated person.

    At least that was the case before LLMs became a thing, now I'm not sure anymore.

  • Obvious spelling mistakes are usually ignored, but there are certain types of writing mistakes that really trigger the type of people that frequent HN.

    For example, use "literally" for exaggeration rather than in the original meaning of the word and you'll likely trigger somebody.

    • I never seen this, unless "literally" really clashed with the intent of the comment (as in, it changed the meaning).

      It's against the HN guidelines to focus on punctuation, spelling, etc, as long as the comment is understood.

      And, in any case, it's now against the guidelines to write using an AI :)

      7 replies →

  • I've been hit by spelling/grammar noise once or twice. Those are usually downvoted and/or flagged.

    • Typos like an/as, of/or, an/and waste the reader's time. That some care be taken to avoid them is no more than common courtesy.

You do all of that when leaving a comment on HN? Why...?

I'm confused by this need(?) desire(?) to polish things that are irrelevant.

  • No, I do not, I mentioned asmuch in my post. But I do not hold it against those that do. I think if you want to make a point across, doing this the most effective way without detracting from the point is a good thing.

    Relevance is in the eye of the beholder.

Would anyone notice if you spell-checked or got narrow feedback about grammar? No. I'm not dang, but perhaps a very reasonable interpretation of the rules is: If the AI is generating the words, don't. If it tells you something about your words and you choose to revise them without just copying words the AI output, it's still your words.

(As an experiment, I took that paragraph and threw it into gemini to ask for spell and grammar checking. It yelled at me completely incorrectly about saying "I'm not dang". Of its 4 suggestions, only 1 was correct, and the other 3 would have either broken what I was trying to say or reduced the presence of my usual HN comment voice. So while I said the above, perhaps I'm wrong and even listening to the damn box about grammar is a bad idea.)

That said, I often post from my phone and have somewhat frequent little glitches either from voice recognition or large clumsy thumbs, and nobody has ever seemed to care except me when I notice them a few minutes after the edit button goes away.

Polish hides your voice. If your composition skills are lacking and you feel that hinders your self expression, set aside some time to improving them: write a short (15 minutes) blog post about some HN topic to yourself in a word doc editor of some sort (Word, Gdocs, LibreOffice, etc); then enable Review Changes and annotate your post for 10 minutes; then, review and accept your changes individually and re-read what you’ve written.

AI is being used as a substitute for skills development when it costs nothing but time to get better. If you’ve reached a plateau with the above method, go find an article or book or interview about editing, pay attention to it and take notes, rinse/repeat.

Spellcheckers will catch grossly obvious errors, but not phonetic typos. AI grammar tools will defang, weaken, soften, neutralize your tone towards the aggregate boring-meh that they incorporated at training time.

Each person will have to decide whether they want individuality or AI-assisted writing for themselves. Sure, some will get away with it undetected, but that’s a universal statement about all human criteria of any kind, and in no way detracts from the necessity of drawing a line in the sand and saying “no” to AI writing here.

Consider the Borg. Everyone’s distinctiveness has been added to the Collective. The end result is mediocre (they sure do die a lot), inhuman (literally), and uniform (all variation is gone). It’s your right if you desire to join the Collective and be a uniform lego brick like the others, but then your no-longer-fully-human posts are no longer welcome at HN.

  • > a word doc editor of some sort (Word, Gdocs, LibreOffice, etc); then enable Review Changes and annotate your post for 10 minutes; then, review and accept your changes individually and re-read what you’ve written.

    Pffff... I'm not going to install LibreOffice for that, or to figure out how to make Gdocs to work with uBlock.

    There is a much easier way. Open LLM chat, type there "Proofread please for grammar, keep the wording and the tone as it is, if it doesn't mess with grammar. Explain yourself." and then paste your text. I don't really know what the tools you mentioned do, but any "free" LLM on the Internet will point to things like missing articles, or messed up tenses in complex sentences.

    You recommend choosing self-improvement, but I just don't believe I can figure out how to use articles. With tenses I think I can learn how to do it, but I'm not going to. I remember there is some obscure rule how to choose the right tenses, but I was never able to remember the rule itself. I'm bad with rules, it is the reason I chose math as my major. There are almost no rules in math, you are making your own rules. The grammars of languages are not like that, they have rules which can't be easily inferred, you need to remember them. Grammars have exceptions to rules, and exceptions to exceptions, and in any case they are not the rules, but more like guidelines, because people normally don't think about rules when they are talking or writing.

    No way I'm starting to learn rules now, I'd better continue to rely on my skills. But LLMs can help me see when my skills fail me.

    > It’s your right if you desire to join the Collective and be a uniform lego brick like the others, but then your no-longer-fully-human posts are no longer welcome at HN.

    I believe you (as most of fervent supporters of the rule here) gone too far onto philosophy with this, too far from the reality and practice. You can't detect AI in my messages, because they are mine. Even when I ask LLM to find words for me, it is me who picks one of the proposed alternatives, but mostly I manage without wording changes. I transfer the LLM's edits by hand by editing the source message, so nothing unnoticed can slip into the final result. If I took the effort to ask an LLM to proofread, it means I care about the result more than usual, so I'm investing more effort into it, not less.

    • An AI may be able to teach you basic grammar but it’s not going to teach you to develop your voice. By design and content training set, an AI today can only pressure you towards the mean of whatever criteria you specify, not away from it. Developing your voice by doing your own proofreading pressures you away from the mean, by helping you double down on what you value most and by choosing which grammatical rules to disregard and when disregarding them is more in-tone for yourself than adherence. I can’t stop you and I won’t remember your handle after an hour has passed (being nameblind is interesting online), so you’ll probably go unnoticed by me, sure. But I still won’t equate regressing to the AI mean with personal growth away from the average masses.

      1 reply →

    • > I'm bad with rules, it is the reason I chose math as my major. There are almost no rules in math, you are making your own rules.

      There's what now? I do think math is flexible but it feels like there are plenty of rules, depending on the context.