alt Hacker NewsI am starting to figure out why AI prose is so hard to parse. AI writes English like it writes code. Which is not surprising given how important coding use case is for LLM vendors. Terse, formal style that lays out information in the order of logic, not in the order of understanding. The reader unpacks sentences the way he or she unpacks lines of code. LLMs are probably specifically trained to reuse code, and flowery Claudisms like "load-bearing" are just "function calls" into a standard semantic library.
Another trait of AI prose is ambiguity. It loves using words or phrases that can are grammatically valid but have two different meanings in two different contexts, and it is up to the reader to look ahead in the sentence and then reinterpret the whole thing. The very common offender is present tense verb vs plural noun (e.g. "tracks" meaning "agrees with" vs "tracks" meaning "plural of track"). This ambiguous English is so statistically prevailing in LLM writing that there has to be a technical reason for this phenomenon.
Reading such text - efficient for LLMs to write, hard for humans to read - is extra labor. And it is no wonder that reader is pissed when suddenly the reading experience becomes an uphill battle.
The last LLM which was fine to read is Sonnet 4.6, but while it writes well, it makes factual errors often.
Replies
I think stuff like “tracks” comes from leagues of the absolutely most condescending technically competent repository in the history of words and letters: stack overflow forums.
And some of the ambiguity I think comes from liability training sets, designed with a preference for not making direct attributions to parties who could claim they were incorrectly characterized. The habit can be seen in like half of Claude messages, where its responses have multiple inert objects or concepts being described through active personalized verbs. Like “the build rejected an undeclared package” as opposed to saying “the build failed because I didn’t update the packages.json.”
> I am starting to figure out why AI prose is so hard to parse. AI writes English like it writes code.
I think sometimes it just writes nonsense. As in there are words there, they're all strung together in a grammatically correct way, and the words are "right", but the sentences just don't contain any actual information.
There have been sentences and paragraphs that I have read over and over, and I just cannot extract any meaning from them. It's very, very strange, and I think that's the uncanny valley of it. It's all there, in the sense of words and grammar, but there's nothing there, the sense of knowledge and meaning.