Comment by mk12
2 days ago
I saw someone say the other day (in response to another blog post being well written) that Anthropic employees have a rule against using AI for writing/external comms? That seems clearly not the case here, normal people don't write like this:
> Most of the path is automated; a person's attention goes where the risk is
> The eval grows with every incident, and every change to the reviewer is scored against all of it.
100%, although if people are getting 90% of their interaction from a robot, one may start to pick up some vocal tics and colloquialisms from machine world. a kind of robo-pidgin.
English isn't my first language, and I'm treating every opportunity to use the language as a way to learn, including extensive discussions with AI at everyday work. Sadly, I'm not noticing any unnatural wording in its replies.
I'm starting to worry about being gradually affected by AI's style through heavy use. It will make me so sad if one day my written piece sent to others is considered to be AI-generated, while it's written with real effort trying to make it sound natural.
Just accept that it will happen, and it will likely happen to all of us. It has already happened to a colleague of mine, and they are a highly educated native English speaker.
Irony being, robots are averaging our best speech patterns. So we're really just syncing humanity's speech patterns, with LLMs acting as proxy.
No it's not averaging. That's only pretraining. Post-training is RL for high approval ratings which isn't necessarily what people speak like but what was rewarded.
Yes this homogenization of not just way of speaking but way of thinking is very undesirable to me. But hey some people might accept the borg.
I've definitely picked up some weird claudeisms. I even know the em-dash keyboard shortcut now.
Macs make it really easy to type a certain few special characters -- em-dash among them. I'm typing on a Windows laptop and I know there's alt+numpad codes but this laptop doesn't have a numpad and I can never remember those. I used to know a few many years ago, but I've forgotten all of them.
Access to a wider array of special characters is also one of the really nice things about touch keyboards on mobile or tablet. Keyboards are great for fast, accurate typing but not for going beyond the basic character set.
I used to use semi-colons and parenthesis in my semi-formal writing, but now I find myself reaching for em-dash instead. I'm not sure if my tone has changed as well but LLM-writing has probably influenced me more than I realize.
Yuuuup. Which I guess makes it even harder to detect what's AI and what's not.
Detecting what is AI and what is good writing is easier than ever now that the AI common speech patterns are established. Reading a well written piece it’s like walking through the park on a beautiful day in comparison to dragging your legs through quicksand
Pangram reports 80% of the text is AI-generated: https://www.pangram.com/history/72309aad-6e3f-4002-bdc5-c062...
I wouldn’t trust the numbers it gives https://news.ycombinator.com/item?id=49023243
Pangram 4 is quite a bit better (that post is about the previous version). IME it’s quite accurate for anything over 500 words or so.
[dead]
> That seems clearly not the case here, normal people don't write like this:
I think when you repeatedly expose and immerse yourself to such a degree in reading and writing language, it brushes off on oneself. So I could also absolutely believe someone from Anthropic wrote this.
agree 100 percent, I write prompts, and at some point I'm going to adjust my style when I see my prompt is ambiguous or something and I bet subconciously I'm going to try to talk like my robot pal when making these adjustments so I could see it happening
this definitely seemed like something claude generated, i know because i frequently do all my research in chat and then ask it to generate a doc based on what we talked about and when i read what it generates the verbosity, the style it writes in makes me delete the whole thing. I would never subject readers to that.
It felt weird reading it because every once in awhile there were some well written sentences and coherent paragraphs, then it fell back into Claudisms.
Another Claude-ism example from: https://www.anthropic.com/research/ecdsa-curve-origins
> This is not a cryptographic break, new attack, or weakness in the ECDSA curves.
I don't think that's a claude-ism because it makes sense to cover this point at the start of the article as a defence against overexcited journalists.
It's only a claudeism when it says "X is not a Y" when no reasonable person would have been expecting that X could be a Y.
Fair, I just feel like I see negated statements significantly more in AI than in human writing. (And, to me, it's poor writing: if it's not an X, it doesn't tell me much, but that's a personal preference.) The newer models also seem to try to stay almost excessively neutral and avoid over-claiming, by writing explicit disclaimers, like this does. So while we employed these patterns in human writing before, I may be becoming overly sensitive to AI writing smells now (like seeing the word "unusually" in any text). Thanks :)
Heavy emphasis on "every" like this is my new Claude smell, after honest and genuine seems to be reduced.
As a non-native, I see how susceptible I am to absorbing such style. There's no way at all for me to perceive anything wrong with the examples you present
It's a bit more subtle than things like "it's not X, it's Y". And even that isn't "wrong", it's just the way AI talks, and therefore an indicator that the author offloaded their thinking to an agent. I've read so much Claude output that it's easy for me to recognize its voice, the same way I could recognize a friend's voice in writing. The examples I quoted are a weird kind of circuitous sentence structure with a certain shape and rhythm that scream Claude to me. Here is how I might rewrite them in human speak:
> Most of the path is automated; a person's attention goes where the risk is
--> We automate as much as possible, focusing human attention on risky parts
> The eval grows with every incident, and every change to the reviewer is scored against all of it.
--> We run reviewer evals against every incident
But that's just my interpretation and my voice. I can't know for sure what the authors would have said if they took the time to write it themselves.
I see. Yeah it's a bit annoying. In my mother tongue, Portuguese, I feel a visceral pain when I read what I classify as bad style. But I never developed such esthetic sense with the other languages in which I can communicate in any level
Personally, a year or two ago writing like that did not really come across as particular bad or AI generated to me, although it was uncommon for humans to write phrases like that. Writing in an unusual way is not inherently bad, it can make your text interesting... but it is less direct and clear than alternatives. But the style becomes unpleasant if you keep seeing the same patterns over and over such as "X'ed against all of it"
It feels like it's trying to sell you something in every sentence.
Yep. It’s the consistent emphasis in every statement that is so draining to me. A human might use a similar tone once or twice in a piece to drive home a particularly important point, but Claude does it with every point. It’s exhausting.
1 reply →
It’s optimized for emotional reaction instead of communication
The one that twigged me was in one of the first diagrams:
> Gradual release > The latest channel first; the stable channel trails it
Such an awkward, Claude-ish way of saying it
If you spend all day reading Claude-written "explainers" of your own codebase, I can imagine the "house style" would rub off on you.
What came first, "Claudish" or those who trained it? I wonder if Anthropic's employees originally wrote like that. It's definitely irritating to read, and IMHO more so than the ESL-grade English which was quite common before AI.
Claudeslop didn’t come from humans, it’s an artifact of running RL on slop outputs. If you keep feeding the slop output back into the model and then training on it, it amplifies its own unique weird vocabulary and behaviours.
The word “gate” was used.
load bearing comment
To be fair, that phrase does not appear in the article.