The real question: did your local LLM write this post?
In any event, not all of us have a unique writing style worth preserving just like not all of us can write clear and clean code. Just saying.
I feel like writing could use a similar harness, where it attempts to minimally reword the authors sentences, perhaps just tweaking grammar, spelling, etc. In the coding example i think the human code would be near unchangeable, the LLM would pivot around it - but in the writing example i think the human writing would have to be more mutable. I imagine it would be a configurable setting.
I've not really seen a system which focuses on this human<->LLM look, but it feels interesting to me.
So the language harness makes sense to me, but corps are already cracking down on token use ( and such a harness would likely only add to the cost ). The other question is whether the people, who could benefit it would even recognize it as a problem though.
Running Alpine/Gentoo/Devuan isn't that expensive. (I'm assuming the cost is time/effort when I say this; let me know if there's another relevant metric)
FWIW, I tried Void and Devuan, but that may have been too early for me then. Naturally, now that stuff mostly works, I am debating whether I can make that attempt again;p
I’m much more willing to read typos and bad writing than LLM writing. If I want to read the LLM rewritten version, I can run an LLM over the original writing myself. I have not yet found true that anyone is better at prompting than anyone else in a way that suggests that I wouldn’t get substantially the same results myself. Thus, I don’t think providing the version that has passed through the telephone game is accomplishing something that couldn’t be done by readers later. I have spent the vast majority of my life reading the original writing styles of people and didn’t have an issue then. I’m not convinced a problem I had was solved when we started post-processing writing with an LLM.
I’m really in the “who gives a shit” camp on something like this. A lot of people probably have an LLM punch up a blog post. It is good at turning bullet points and notes into prose, fixing run-ons, etc. Maybe I’m naive but I trust that the kind of person who posts a clearly noncommercial post like this on HN gives a crap enough that they read the final draft and confirmed it isn’t inaccurate.
This pearl-clutching about the mere use of AI regardless of how responsible or appropriate the use is, seems like a professor in 1985 throwing an essay back in a student’s face as “this was obviously printed from a computer and not typewritten like a PROPER essay! I can tell just by looking at it!”
Slowly but surely, I had to remove my beloved lists, emojis (though LLMs do less of that now, maybe I can incorporate them back), and emdashes.
There are no usable tells that apply generally in the first place. Pretty much all of the hyped-up memes in circulation about how to detect LLM output are highly unreliable.
LLMs write the way they do because they are trained on common patterns of human writing. All of the tropes people point to in LLM output are there precisely because they've already been in widespread use for some time.