It's like... oh my god, dude, even I, an actual human, don't have that much of self-reflection, so could you just stop writing apologia, please, and switch to actually doing the task?
This inspired me to add a "No AI-isms" section to my CLAUDE.md, which has cut the typical claude-flavored tells a lot in recent sessions. Roughly:
- No preamble validation or self-flagellation: "You're right to push back", "That's on me", "I appreciate you pressing on this", "I should have caught that sooner". When I correct you, say what's actually true and move on. One short "you're right, X was wrong" is the ceiling.
- No unrequested retrospective section ("What I'd do differently", "Going forward I'd be more deliberate about..."). Fix the thing instead.
- No dramatic one-line paragraphs for emphasis: "It wasn't.", "That is the shift.", "And that matters.", "That is the analysis." Keep the sentence inside its paragraph.
- Don't narrate the shape of your own answer: "Stepping back, there are two things happening here", "The distinction matters", "The better framing is not X so much as Y", "Put differently", "To be candid". Say the thing once, plainly.
- Words to avoid unless literally accurate and a normal person would say them: load-bearing, seams, smoking gun, directionally, first-order, legible, parsimonious, recalibrate, coordinate system, holds multiple truths, productive tension, category error, "the honest answer is".
- No hedging both directions to avoid committing ("may still be defensible, but", "not exactly resolved, but"). Give the call plus how sure you are, or say you don't know and what would settle it.
- Don't end on a flourish or a paradox ("the clarity revealed more complexity"). End on the answer, or on a next step that names a real command or file.
- A "next step" has to be runnable or checkable. "Take a step back and revisit with the updated framing" is not one.
I actually think the fact Claude has certain mannerisms is kind of to be expected, isn’t it? If you talked to the same person every day all day I’m sure you’d be quite attuned to their habits of speech. Thinking about a friend I talked to today, I can immediately think of some (“dude! I know!”).
I wonder how people would react if, rather than a consistent manner of communication, it was something different every day. One day it would be like talking to a 15-year-old who’s really into anime. The next day, a British gentleman. And so on. Would this be any better? It would probably be rather annoying and we’d just want Claude to go back to sounding like Claude.
I agree that consistency beats a random persona per session.
Most of what I listed isn't about personality though, it's filler that imitates structure. "Stepping back, there are two things happening here" before a four-sentence answer isn't a habit of speech, it's a table of contents for something that doesn't need one.
I vouched for your comment not because I think this is or isn't helpful advice (I have no idea), but just to thank you for the concept of "narrating the shape of one's own answer". It's something that often annoys me, though I'm sure I often do it myself, but I never thought about what it is, exactly, I just filed it under the generic category of bloat.
It's genuinely useful in speech, which is why a lot of people do it. A listener can't scroll back, and it buys you a second to think. In writing both of those things go away and it becomes pure bloat.
I wonder if these emerged from models being trained on a lot of transcribed talks and videos?
A friend of mine had a really good technique with parenting. He taught his kids the saying 'Funny once'. Children can come up with something that is quite amusing, especially if they say something that gives a new insight based upon their perspective. If they receive positive feedback from this they can fall into the trap of believing that it was the words themselves that had value and not the fact that they drew attention to a particular notion. Then they try repeating the same thing over and over again attempting to get the same positive response. Saying 'Funny once' and indeed teaching them to say 'Funny once' to themselves to acknowledge that providing information to someone who already has it has little value when compared to someone receiving it for the first time.
Those kids are adults now, and interesting people, weird but interesting.
[Almost all of my friends had weird kids (spectrum genes? Who knew? (Dear reader, Everyone knew)). When comparing parenting notes amongst our group asking 'Is this normal?' the frequent response was 'how would we know?']
Indeed, There's a reason I provided a reflective story that conveyed what I wanted to say without being confrontational.
On the other other hand there is a difference between not knowing something that a group knows, and informing a group of something that only one of them does not know.
The problem could be either that you are not communicating appropriately for the audience,or that you are unaware of the actual knowledge level of the audience. A person may be prone to either of these by being the one in 10,000, so they shouldn't be berated. So I chose to stick to offering information myself.
> I'm wondering what are Claude's common phrases in other languages?
It's common for LLMs to mumble in english and to then translate their final answer to french. Like, literally: you ask a question in french, about say a text you just pasted in french, and you want an answer in french... Well, you still get to see all the loud intermediate "thinking" in english.
You are right to push back on this. I should be more explicit. My honest take is that this is, in fact, my honest take. I appreciate you holding me accountable here.
I was probably there when they invented that term, LOL (I first heard it in the Ruby startup space years ago, I think). I still think it's meaningful, along with "design smell". Why? Because it speaks to coding as craft, not just as purely-rational engineering. The design of things matters, and yet, design is (mostly) "irrational"... just like smells.
It shoots itself in the foot, though- Smells don't really have a real consequence*; bad design does.
Honestly, you're right. I didn't listen to you and that's on me. And from now on, I'm going to tell you everything you need to know - no fudging, no white lies, no speculation, just the truth.
