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.
Fair hit, and I'm not going to try to argue you out of a gut reaction to the prose. If it read as slop to you, that's on me.
But, I'd rather know if the claim actually held: is there a forget decay operation anywhere in the current stack, or not? That's the part I want people to hit.
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.
It's kinda fascinating how far LLM coding/problem solving has come without making much progress on the annoyingness of their writing. Any theories?
The LLM-voice revulsion isn't just about particular idiosyncrasies. Another commenter put it well - the "uncanny valley of text".
But, I'd rather know if the claim actually held: is there a forget decay operation anywhere in the current stack, or not? That's the part I want people to hit.
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.