It's a very good observation. I don't know if I'd call it "forgetfulness" in the context of a current [2026 edition] LLM. They are very good at remembering almost every "thing" that passes a certain token-density threshold, until they hit saturation, and then it's a sheer rockface down to the abyss of unnatural hedging and reconfirmation of basic premises. Some sort of "forgetfulness" as described would introduce more moving parts into the "inference" stage of the running of an LLM, introducing statefulness/state-tracking.
I'm getting to the point that I almost have a physical feeling of revulsion/nausea when I read something outside an open Claude Code session that is written in an AI voice.
I'm so sick of that voice -- word choice, phrasing, style... it's hard to define and frustrating because it's both pervasive, influential on human writers including myself (I found myself using the phrase "doing a lot of work" in a Slack message about a word someone chose to use :grimace:), and presumably compounding on future LLMs.
Same here. I started describing it as the “uncanny valley” of text. It’s like a gut reaction that something is off with the text even if you can’t pinpoint it immediately.
I concur. It's interesting that this seems so difficult to get rid of; despite actively trying to overlook the taste of LLM writing, it still grates, and this does not happen to me in the same way even with communication from half-illiterate human idiots.
It's kinda fascinating how far LLM coding/problem solving has come without making much progress on the annoyingness of their writing. Any theories?
Not that it's an ideal solution, but you have all the tools you need to do something about it. You can put all your preferred writing style guidelines into an LLM and have it ingest and rewrite any text you dislike.
Only if the problem is ideological, ie. you don't like the "idea" of llm's. But if in fact your actual dislike is the style of writing, then you can simply change the defaults. It's pretty easy to make a llm conform to your preferred style, avoid the use of em-dashes, or reduce verbosity, etc.
Wanted to say I am with you 100% here. I'd bet my dingly doo on it being pure LLM. As well as the others. My question is how can this shit be kept out of here and elsewhere... This example is easy to catch, others less so.
I almost don't want to discuss the tells, because they'll immediately be ingested into training.
I can understand someone wanting to test or play around a bit, but this could obviously become a serious problem, not to say it hasn't already, but I don't pay deliberate attention to it.
HN policy actually makes it a violation to call this shit out, technically. I suspect they will make exceptions.
It's a very good observation. I don't know if I'd call it "forgetfulness" in the context of a current [2026 edition] LLM. They are very good at remembering almost every "thing" that passes a certain token-density threshold, until they hit saturation, and then it's a sheer rockface down to the abyss of unnatural hedging and reconfirmation of basic premises. Some sort of "forgetfulness" as described would introduce more moving parts into the "inference" stage of the running of an LLM, introducing statefulness/state-tracking.
[flagged]
I believe the title is true for humanity at large, more and more over time. These things cut both ways, for both good and ill.
There is so much weight in this one comment. I feel it now!
No, but you can reprogram it and send it back in time to undo itself.
Ugh, another LLM-voice article.
I'm getting to the point that I almost have a physical feeling of revulsion/nausea when I read something outside an open Claude Code session that is written in an AI voice.
I'm so sick of that voice -- word choice, phrasing, style... it's hard to define and frustrating because it's both pervasive, influential on human writers including myself (I found myself using the phrase "doing a lot of work" in a Slack message about a word someone chose to use :grimace:), and presumably compounding on future LLMs.
Same here. I started describing it as the “uncanny valley” of text. It’s like a gut reaction that something is off with the text even if you can’t pinpoint it immediately.
I concur. It's interesting that this seems so difficult to get rid of; despite actively trying to overlook the taste of LLM writing, it still grates, and this does not happen to me in the same way even with communication from half-illiterate human idiots.
It's kinda fascinating how far LLM coding/problem solving has come without making much progress on the annoyingness of their writing. Any theories?
Sounds like that word was pretty load-bearing
It's probably doing a lot of heavy lifting.
I need to push back on this comment.
Not that it's an ideal solution, but you have all the tools you need to do something about it. You can put all your preferred writing style guidelines into an LLM and have it ingest and rewrite any text you dislike.
That's like saying a robot will be a better friend if I use a more skin-like material for its face.
The LLM-voice revulsion isn't just about particular idiosyncrasies. Another commenter put it well - the "uncanny valley of text".
Only if the problem is ideological, ie. you don't like the "idea" of llm's. But if in fact your actual dislike is the style of writing, then you can simply change the defaults. It's pretty easy to make a llm conform to your preferred style, avoid the use of em-dashes, or reduce verbosity, etc.
If only there was a smoke test for this kind of thing.
[flagged]
You LLM-generated this comment too. What about you (the human, if there is one behind this account) -- what do you think?
If you don't speak English, write it in Hindi and use google translate. That will be much preferable to something written by an LLM.
Wanted to say I am with you 100% here. I'd bet my dingly doo on it being pure LLM. As well as the others. My question is how can this shit be kept out of here and elsewhere... This example is easy to catch, others less so.
I almost don't want to discuss the tells, because they'll immediately be ingested into training.
I can understand someone wanting to test or play around a bit, but this could obviously become a serious problem, not to say it hasn't already, but I don't pay deliberate attention to it.
HN policy actually makes it a violation to call this shit out, technically. I suspect they will make exceptions.
It’s just like me fr fr
We are a region
legion
fr haha except you can forgive maybe? that's the DLC the model never shipped with
unless you can't, then wait, are u agi?
That shi be bussin fr fr no cap