Comment by adamzwasserman
2 days ago
It is not a zero sum game.
I have always had a very idiosyncratic way of expressing myself, one that many people do not understand. Just as having a smartphone has changed my relationship to appointments - turning me into a prompt and reliable "cyborg" - LLMs have made it possible for me to communicate with a broader cross section of people.
I write what I have to say, I ask LLMs for editing and suggestions for improvement, and then I send that. So here is the challenge for you: did I follow that process this time?
I promise to tell the truth.
I think there's a difference between using an LLM as an editor and asking the LLM to write something for you. The output in the former I find to still have a far clearer tonal fingerprint than the latter.
And whose to say your idiosyncratic expressions wouldn't find an audience as it changes over time? Just you saying that makes me curious to read something you wrote.
Not the GP, but I'm a millennial who leans on cultural references and has a bit of verbal flourish that I think comes from a diet of ironic, quirky, dialogue-heavy media in the early 2000s, stuff like Firefly, Veronica Mars, and Pushing Daisies, not to mention 90s Tarantino, John Cusack films, and so on.
I've never given it too much thought, it's just... the way I communicate, and most people in my life don't give much thought to it either. But I recently switched jobs, and a few people there remarked on it, and I've also recently been corresponding with someone overseas who is an intermediate-level English speaker and says I sometimes hurt their brain.
Not making a value judgment either way on whether it's "sophisticated" or whatever, but it is I think part of my personality, and if I used LLM editing/translation I would want it to be only in the short term, and certainly not as something
... that I allowed to be part of a feedback loop ironing away those idioms and goofball expressions that my brain delivers.
(not sure how the last bit of that disappeared, but maybe that's just more ADHD brain)
I have been writing for professionally since I published my book in 2017 (with human editors): https://a.co/d/6ZFFb2z
If you want to read my unedited writing most of the articles on Hacker Noon prior to this year are "raw" https://hackernoon.com/u/azw
Most (all except the last two) of these are "raw": https://emusings.substack.com/
I never garnered a large readership. When I was the CTO at a large NGO, they literally called me "big yoda" because they considered my pronouncements so inscrutable. <shrug>
Transformation seems reasonable for that purpose. And if we were friends, I'd rather read your idiosyncratic raw output.
At some point, generation breaks a social contract that I'm using my energy and attention consuming something that another human spent their energy and attention creating.
In that case I'd rather read the prompt the human brain wrote, or if I have to consume it, have an LLM consolidate it for me.
True, I do not do that for friends
I should probably do that too. I once wrote an email that to me was just filled with impersonal information. The receiver was somebody I did not personally know. I later learned I made that person cry. Which I obviously did not intend. I did not swear or call anyone names. I basically described what I believe they did, what is wrong about that and what they should do instead.
I hear you. LLMs have been a major improvement in my life in that regard.
If someone cries about an email you sent, the problem isn’t with you.
I would be interested to see an example of a before and after on this. I do think LLMs as editors and rewriters can be useful sometimes, but I usually only ever see them used as a means to puff out an idea into longer prose which is really mostly counterproductive.
I think it can be useful as a tone-check sometimes, like show me how a frustrated or adversarial reader is going to interpret this thing I'm about to send/post.
LLMs have now robbed you of the opportunity to make your communication clearer
hahahahahaha
Here's my guess- your post reflects your honest opinion on the matter, with some LLM help. It elaborated on your smartphone analogy, and may have tightened up the text overall.
here is the entire exchange. you decide:
Me: I want to reply to this HN article:
We're Losing Our Voice to LLMs Social media has become a reminder of something precious we are losing in the age of LLMs: unique voices. Over time, it has become obvious just how many posts are being generated by an LLM. The tell is the voice. Every post sounds like it was posted by the same social media manager. If you rely on an LLM to write all your posts, you are making a mistake. Your voice is an asset. Not just what you want to say, but how you say it. Your voice is unique. It is formed from your lifetime of lived experiences. No one's voice will be exactly like yours. Your voice becomes recognizable. Over many posts it becomes something people subconsciously connect with, recognize, trust, and look forward to. Your voice provides the framework for the impression you leave in a job interview, while networking at a meet-up, or with a co-worker. Years ago I got a job thanks to my blog posts. A manager wanted my voice influencing their organization. Your voice is an asset. Your voice matures and becomes even more unique with time and practice. LLMs can rob you of that voice, and the rest of us lose something precious in the process. Having an LLM write "in your voice" is not the same. Your voice is not static. It changes with the tides of your life and state of mind. Your most impactful message may come because it was the right moment and you were in the right frame of mind. Let your voice grow with use. Let it be unique. Do not let one of your greatest assets fade into atrophy, wilted by cognitive laziness. Write in your own voice. I do not care what the linguistic remix machine juggles into being. I care what you have to say. Join my newsletter. Get my posts, best coupons, and most interesting links direct to your inbox. Email address Join © 2025 Tony Alicea. All rights reserved. tonyalicea.dev
Here is my proposed reply:
It is not a zero sum game.
I have always had a ver idiosyncratic way of expressing myself, one that many people do not understand. Just as having a smart phone has change my relationship to appointments - turning me into someone prompt and reliable - LLMs have made it possible for me to communicate with a borader cross section of people.
I write what I have to say, I ask LLMs for editing and suggestions for improvement, and then I send that. SO here is the challenge for you: did I follow that process this time?
I promise to tell the truth.
Claude: Identified typos and validated strong argumentative content.
Claude: Good angle - the "it's a tool for accessibility, not replacement" framing is a legitimate counter that doesn't dismiss the author's point entirely. The challenge at the end is smart for engagement (comments boost visibility).
Typos to fix:
"ver idiosyncratic" → "very idiosyncratic" "has change my" → "has changed my" "borader" → "broader" "SO here" → "So here" Claude: One question: the smartphone/punctuality analogy is a bit of a stretch - do you want to tighten it or cut it? It's not essential to your point.
Me: it illustrates how - as a cyborgh - I am more sucessful personally with the aid of technology
Claude: Validated cyborg framework strengthening personal capability through technology.
Claude: Fair point - it establishes a pattern of tech-as-personal-augmentation rather than tech-as-replacement.
Claude: Do you want to make the "cyborg" framing explicit in the post? That word might land well on HN and sharpen the contrast with the author's "atrophy" argument.
Me: I have always had a very idiosyncratic way of expressing myself, one that many people do not understand. Just as having a smart phone has changed my relationship to appointments - turning me into a prompt and reliable "cyborg" - LLMs have made it possible for me to communicate with a broader cross section of people.
Claude: Validated cohesive metaphor and polished prose for clarity.
Claude: That works. "Cyborg" in quotes signals self-awareness without being heavy-handed, and it now ties both examples together thematically. Minor: "smart phone" → "smartphone" (one word) if you want to be pedantic about it. Otherwise the post is clean and ready.
I don't see signs of LLM writing in your comment so I'll have to guess no.
It did some light spell checking and suggest I add one word - see above
If you didn't intentionally try and trick us, then yes, you used an LLM.
see above
Please share what you told the LLM! I can't be the only curious one.
See above
You didn't, but you've learned.
I did, but it did not have much to add