Hacker Newsnew | past | comments | ask | show | jobs | submitlogin
mk121 day ago | parent | context | favorite | on: How the Claude Code team does code review 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. help 
jazzyjackson1 day ago | next[–] 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. reply talldeck9 hours ago | parent | next[–] 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. reply grosswait6 hours ago | root | parent | next[–] 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. reply TeMPOraL14 hours ago | parent | prev | next[–] Irony being, robots are averaging our best speech patterns. So we're really just syncing humanity's speech patterns, with LLMs acting as proxy. reply bonoboTP42 minutes ago | root | parent | next[–] 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. reply jazzyjackson6 hours ago | root | parent | prev | next[–] 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. reply levkk1 day ago | parent | prev | next[–] Yuuuup. Which I guess makes it even harder to detect what's AI and what's not. reply timacles8 hours ago | root | parent | next[–] 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 reply cjkhowes19 hours ago | parent | prev | next[–] I've definitely picked up some weird claudeisms. I even know the em-dash keyboard shortcut now. reply wffurr11 hours ago | root | parent | next[–] 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. reply nickspacek14 hours ago | root | parent | prev | next[–] 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. reply bonoboTP43 minutes ago | prev | next[–] Heavy emphasis on "every" like this is my new Claude smell, after honest and genuine seems to be reduced. reply paimapi1 day ago | prev | next[–] Pangram reports 80% of the text is AI-generated: https://www.pangram.com/history/72309aad-6e3f-4002-bdc5-c062... reply phoghed10 hours ago | parent | next[–] I wouldn’t trust the numbers it gives https://news.ycombinator.com/item?id=49023243 reply zeroonetwothree9 hours ago | root | parent | next[–] 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. reply lavezzi1 day ago | prev | next[–] > 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. reply cowboylowrez9 hours ago | parent | next[–] 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 reply jansport1231 day ago | prev | next[–] 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. reply atty23 hours ago | prev | next[–] 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. reply afro885 hours ago | prev | next[–] 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 reply brof17 hours ago | prev | next[–] 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. reply sebzim450011 hours ago | parent | next[–] 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. reply brof6 hours ago | root | parent | next[–] 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 :) reply myth201823 hours ago | prev | next[–] 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 reply mk1220 hours ago | parent | next[–] 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. reply myth20189 hours ago | root | parent | next[–] 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 reply versteegen14 hours ago | parent | prev | next[–] 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" reply wannabe4420 hours ago | parent | prev | next[–] It feels like it's trying to sell you something in every sentence. reply drewbeck5 hours ago | root | parent | next[–] 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. reply jambalaya85 hours ago | root | parent | next[–] agreed. reply timacles6 hours ago | root | parent | prev | next[–] It’s optimized for emotional reaction instead of communication reply wffurr11 hours ago | prev | next[–] If you spend all day reading Claude-written "explainers" of your own codebase, I can imagine the "house style" would rub off on you. reply userbinator15 hours ago | prev | next[–] 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. reply MisterMunchkin14 hours ago | parent | next[–] 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. reply damontal20 hours ago | prev | next[–] The word “gate” was used. reply ta9375482912 hours ago | prev[–] load bearing comment reply fn-mote9 hours ago | parent[–] To be fair, that phrase does not appear in the article. reply
Consider applying for YC's Winter 2027 batch! Applications are open till November 2. Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact Search: