AI Is Great for Writing, So Why Is Everything It Writes Unreadable?
I don't want to read what you didn't write
Colin Breck argues that AI-generated design docs, pull requests, and messages are unreadable because they lack the context and vulnerability of human writing. Drawing on survey data showing 78% of readers stop at AI-scented posts and insights from Bjarne Stroustrup and Simon Sarris, he explains why AI works for verification and abstracts but fails at authentic communication—and how tools like Pangram might enforce the social contract between writer and reader.
To use an LLM to write is to void the social contract between writer and reader: we readers shouldn’t be expected to labor to understand a sentence that the writer themselves didn’t work to create.
- hatthew
As I have been saying for years:
Writing is fundamentally the transfer of information from your brain to my brain. If you have 1000 bits of semantic information you want to transfer, you can't give 300 bits of semantic information to an LLM and have it fill in the remaining 700, because it doesn't know what those 700 bits are. If it's able to guess those 700 bits correctly, then they aren't true semantic information, and you really only have 300 bits you want to transfer. You might as well transfer those bits to me directly, rather than having the LLM add on an extra superfluous 700 bits that I then have to filter out.
- dandare
>I had someone write me a personal message about a sensitive topic that was clearly workshopped with AI in an effort to nuance the conversation and not offend me. But the message became impersonal, dispassionate, and disjointed. It had all of the parts, but it didn’t make sense as a whole. I wasn’t interested in reading it, or responding. I would much rather someone be themselves and write with their own voice, or with some passion, even if they can’t quite find the words, or risk offending me.
Only a privileged person can say this. Not everybody is a native speaker or good communicator. As an IT guy somewhere on the spectrum, I have damaged my career on multiple occasions by clumsy writing.
- zmmmmm
It's funny, i push back on pull requests because there is too much description now - a 20 line change has pages and pages of generated description, rationalisation for why it is safe, defense of each design decision, analysis of risks and side effects. People are indignant, you're rejecting my change because there is too much documentation? And my response is, I don't have time to read it and you put me in the position where I can't afford not to - because approving the PR implies I did and accepted it. The investment to read all that for the value of a code change that I'm one prompt away from doing myself if I cared is just not high enough. So it's rejected.
- iforgotmypasswo
I kind of agree with this, but I think it’s model specific and a temporary problem.
Opus 5 and Fable 5.1 commit/PR messages are incomprehensible garbage.
However, Astra messages are nearly perfect for a copy/paste to less-technical stakeholders. I maybe fix a line or two.
Give it a year, and I suspect that I won’t even need to make those fixes.
The only problem right now is I can’t get my team 20x OpenAI accounts due to supply constraints. We’re all stuck waiting, hoping Anthropic either ups their game or OpenAI gets more capacity.
We would easily pay $1000 a month per developer/PM for a business tier ~30x account or similar that let everyone use Astra all week without running out of tokens. And that is entirely because of the writing and communication improvements.
- gfody
> People who rarely produced original writing are suddenly producing
these posts are beginning to make me wince. ai is giving voice to a lot of folks we probably wouldn't even be hearing from otherwise - because not everyone does their thinking in articulate prose, and extracting their realizations as shareable language takes effort, or long, embarassing iterations with ai "workshopping" to get to something they can read back and go yes this is what I am trying to say.
now the sentiment is that whatever these people had to say they could have just come out and said it - and that would be more passionate and less disjointed - no, not necessarily, and the more it gets repeated the more it's sounding elite and pompous to me. for example this:
> I had someone write me a personal message about a sensitive topic that was clearly workshopped with AI in an effort to nuance the conversation and not offend me. But the message became impersonal, dispassionate, and disjointed. It had all of the parts, but it didn’t make sense as a whole. I wasn’t interested in reading it, or responding.
this reads as someone choosing to ignore a personal message about a sensitive topic - because of an assumption they made about their writing: that they workshopped it when they should not have - because whatever it was they were struggling to say they should have isntead trusted the author to be able to understand the precise meaning of their raw, inelegant thoughts no matter how embarrassed they might be […]
- earthnail
I'm going to be a bit contrarian here. In general, I 100% agree, just send me the prompt; however sometimes I feel an LLM can help structure thoughts. It can be a good sparring partner. If you proofread your LLM content, re-prompt until it sounds right and no longer like AI content, and feel that it actually conveys the information incredibly well, then I'm happy.
One of the instructions I've hammered into Claude is "Write like a human. I don't want this to sound like AI content. Your standard style of writing would fail miserably if it was reviewed by an English teacher. I want you to write prose that is nice to read. For example, write full sentences instead of bullet points."
It works wonders. Suddenly, my plan documents are something I actually understand, and something I'd be happy to share as an RFC. They still need iterating every time before they're ready to share, but I no longer have "the honest truth is" and other BS in my output. It's so refreshing for my brain to be able to actually focus on the content.
I've noticed this with my partner, too. She used Claude to draft a strategy document and felt completely overwhelmed. A classic moment of "AI did all the thinking for me, but now I don't know what I'm presenting". Once I helped her prompt Claude into writing the strategy in proper English, she understood what the AI was proposing, rejected large parts of it, iterated several times and ended up with a draft document where she edited the finishing touches herself a […]
- blandcoffee
I appreciate the direction of this article, and commend the author on publishing work, but the first sentence in the first paragraph is exactly what they lament.
> A pattern I see is that people use AI to build something new, then they use AI to retrospectively summarize what they have already built into a design document. Reading a document like this isn’t just difficult—it is punishing.
- jmcgough
"Reading a document like this isn’t just difficult—it is punishing."
I can't tell if this essay was written in earnest or as a subtle troll.
- addisonj
On the note of imperfections... My preference is now strongly towards reading someone's stream of thought thrown down at speed over than that same stream of thought shat through the digestive track of an AI agent. At least that feels human.
To me, it also seems like they AI digestion is getting actively worse? As best as I can tell, all the agentic nature and reasoning for code is now making writing actively worse, as the agent pulls across your whole knowledge base and will take that one thought and eagerly join and context it thinks is relevant, with the reasoning spread throughout the page.
- kimjune01
The most sensible solution that I've seen so far is to delineate human spaces from LLM spaces. Technical mumbo-jumbo can be LLM as an artifact, and human thought can just point to them.