DE version is available. Content is displayed in original English for accuracy.
Advertisement
Advertisement
⚡ Community Insights
Discussion Sentiment
48% Positive
Analyzed from 4965 words in the discussion.
Trending Topics
#context#claude#don#own#something#same#answer#point#more#human
Discussion (119 Comments)Read Original on HackerNews
Write as yourself. You’re being paid for your expertise and insights. Communicate them directly to us. Copying and pasting Claude responses into Slack or an email directly shifts the burden of comprehension and understanding to everyone else, and worse, risks skipping that step for yourself. Even if you’re fundamentally using Claude to gather your thoughts or help you prepare a response, you need to be writing it yourself, in your own voice. Not having Claude ape your voice, or “make it sound less like AI”. You, directly. Doing this will further reinforce your own understanding of the state of things, the same way teaching someone is the best way to learn. As a guideline: for Slack and email comms, this should be near-universally written as you. For deliverables that are longer form and follow a template like proposals, roadmap/discovery work, etc., use of agents is expected but, see Principle #2. (Own the Output.)
What you wrote just seems common sense to me, and I'm hopeful it will emerge as such given enough time.
As such, isn't the question really about
1) whether it was communicated clearly/effectively 2) whether it should have been communicated to others at all (rather than something that you just dealt with yourself)
As for the writer being paid to use their expertise, learn more things etc: absolutely. But they could spend whatever time is required to think about the issue and then still have Ai write it at their direction. And, regardless of who wrote it, it could still be poor, irrelevant or misleading.
I'm not defending AI over-usage, but you folks evidently haven't thought about any of this nearly sufficiently enough... and the policy doesn't seem to be addressing what it ought to be: whether everyone is actually thinking, learning, discerning, deciding etc...
Ps I passed your comments to chatgpt and asked what it thought about it all, and it missed all of this. But then agreed once I brought it all up. Then it did a poor job of writing it's own response. I couldn't be bothered to guide it towards something more appropriate. https://chatgpt.com/share/6a86cc31-f058-83e8-8abd-3921b518ec...
I think your linked chat demonstrates quite well why you are wrong.
The sender's burden is a few lines of text "Write me $FOO, conclude with $BAR".
The recipients burden is an order of magnitude greater, trying to find your conclusion in hundreds of lines of text.
After all, your initial line:
> But isn't that "burden" on others always going to be there, whether you or AI wrote it? That's what communicating is...
Is concise and clearly understandable in 21 words . I understand your point even if I don't agree with it.
The linked chat has 1424 words. Your point is in there somewhere, but now you want the recipient to play "Where's Waldo" to find your point.
(BTW: I can't believe just how effectively you argued against your own point! I have never seen someone do it as effectively as this in all the time I have been reading HN)
Not the same burden.
The value of the person is digesting and giving the materially important stuff in the answer (including their expertise and opinion). Not the AI diarrhea.
I think it can be OK if AI is used to polish up one’s message or to help structure it. Basically help with grammar, formatting, and wording.
But copy pasting an AIs response to a question? Not at all. People earn a reputation over time. TRUST is earned. An AI cannot earn trust. If you copy paste an AI response verbatim, i need to read everything in your message with a big grain of salt. Imagine doing this all the time as a reader? Exhausting and a waste of others time. If i want to read raw AI output i’ll ask the AI directly, thanks.
If you write something in your own words, or at least synthesize an AI response before sharing it with me, then i know i’m reading something that has at least passed the smell test.
It’s the difference between reviewing a pull request from an intern and a principal software engineer.
And because most ai's are not concise we blame ai's for faults we don't like in humans either: being longwinding
https://www.anthropic.com/learn/claude-for-you
This framework provides a more abstract way of thinking when working with AI systems. Especially valuable to me is the pattern of the 4 D's: Delegation, Description, Discernment, and Diligence, which I have now internalized whenever I use AI systems. It helps me understand my own and others' (mis)use of AI systems a bit better.
Like is your insight that copying and pasting something is not understanding it? Do people seriously not known this?
There is no need to Socrates when writing policy docs. Maybe this is why people ignore reading your actual voice messages that you feel a need to also justify this basic request. Sometimes the human voice thinks too highly of itself also.
And maybe GP doesn't want that.
For purposes of training the AI (enablement firm)?
> Write as yourself.
Unless it's your first day on HN (it's not 2008 account), most people use paragraphs and sentences longer than 2-5 words. Something like "You, directly." in the middle of all that has a certain vibe to it.
> Copying and pasting Claude responses... directly shifts the burden of comprehension
Most definitely.
The problem is we live in a world where people try to pass off copy pastes as their own all the time, many even smart enough to remove the em-dashes now. So I don't think that's going away soon. Your first sentence seems human, the rest doesn't match the tone at all.
Isn't that the very thing you just claimed people don't do?
For simple, impactful sentences, I often use short ones. They work better.
Since people started using Claude now I get full context of everything… might be too much sure, but to be honest over-communicating seems better than under-communicating - sure it’s boring and tedious but that shifts the blockage to me.
Otherwise each of these coaxing sessions is something I have to keep in my head until resolved, which is a load in and off itself.
And even better - I can point Claude to that message and gives me a summary. You might say this is silly because we are paying the LLM tax, but knowing what to share, and then verifying against my situation are two different things.
Sometimes they have checked the wrong thing, sometimes they need guidance, sometimes I need to investigate before I can answer. A full LLM message with context is like “summary of their working context that I can resume on my end” so I don’t waste cycles asking or rechecking etc.
And it is still possible to be a learning experience for both of us since the initial message is the start, we can then talk to each other like humans, both much more in sync than before…
It is kinda ironic but I think it does push things in a better direction. Would I have loved it if the message was human, direct and to the point - obviously, but we are all busy, we got shit to do, and this is a useful “resume” mechanic
I'd argue that it's worse because now you have no idea what the actual original context was, just the AI's hallucination of it.
And I think this is where one key argument on the page itself I think fails:
> The person on the other side has the same tools you do.
Yes, the person on the other side has Claude; but in many cases, their Claude doesn't have the same context as my Claude. Saying, "This thing happened in an area of the code I don't have any expertise in. Below is Claude's analysis, which I'm not qualified to assess" is I think a valid time to copy and paste LLM output. [1]
The other thing to say is that it can be a "LMGTFY" style response; i.e., "Why did you ask me that, when you could have gotten a perfectly good answer from ChatGPT?"
[1] In the particular case I'm thinking about, it was a bug in an ocaml component; I don't know ocaml or need to know it; handing Claude's analysis 'caveat emptor' to the maintianers who do know ocaml I think is more helpful than not.
I’m reading a bunch of game modding discords, and this exactly what happens, and what’s hated. Because Claude is also not qualified to assess it. Not by default. The modder’s Claude might be because of the extra context and steering, but the user’s produces usless slop, instead the actual log, and context what the user did is what’s helpful.
I’d say this (when you don’t understand it yourself) is pretty much the worst time to send AI output.
Quick edit: Yeah, I get it in situations like GP where the user is unhelpful, doesn’t want to learn, doesn’t care, and you also can’t tell them to fuck off. But just because the user gives Claude the context they should have given you in the first place, doesn’t make it good.
1. I've experienced both (ai paste slop & ai providing helpful context that would otherwise have been absent) but the former has been a much bigger problem than the purported benefits of the latter
2. before the advent of LLMs, I had fairly strong contrarian opinions on the latter (clueless users asking questions with no detail) that I still hold to this day. A good proxy for my opinions on this is that I think https://nohello.net/ is a crutch for undersocialised (or overworked/near-burnout OR undiagnosed autistic) engineers & should not be normalised. The origin of this sentiment is users entering a quiet IRC room & saying "hello", then leaving & not being around when someone eventually replies: in that context nohello is pragmatic, but taking it beyond that to modern high-frequency realtime chat is an antisocial overstep. Leading with the entire context of your query may have some practical benefits but they're honestly overstated in exchange for killing natural social tendencies towards human dialogue. Similarly, a non-technical user giving you zero info about a problem is an opportunity for conversation & mutual education. It's relationship-building & helps build a foundation for further interactions with this person. It was never a problem in the first place; "solving" it is just another milestone on the road toward de-socialising humanity.
I would love to spend more time and talk to the people with their issues so we can come to a common understanding… but neither have the capacity for this, and now things are getting worse I think.
Maybe someday agents are good enough that we just discuss direction and implementation details, and every “developer” becomes more of an executive in a company, free to chat about more than just work, focusing on building human relationships and leaving “the tech stuff” to their agent teams…
And old geezers like us who actually know how to write ourself out of a for loop would be the premium - wizards holding forgotten knowledge, incomprehensible to mere uninitiated mortals. I wonder what distinctive dress and hair styles will we develop :-D
> a lot of my colleagues messages are “x broken” or “I do y”
These people had below than average communication skills (or at least they were putting below than average effort communicating with you), so LLMs improved their output.
However, the society kinda expects people can and Should improve themselves over time. The issue is that LLMs improved their output, but not necessarily them.
Context is everything.
Btw, Claude code sent my first accidental AI email yesterday. I guess permissions changed? Before it could only draft. Uhoh, waiting for the onslop.
> Since people started using Claude now I get full context of everything… might be too much sure, but to be honest over-communicating seems better than under-communicating - sure it’s boring and tedious but that shifts the blockage to me.
Yes, but the kind of engineer that used to say "X is broken" will send you some slop with missing context and Claude will try to apply general solutions from its training data rather than from the specific context. As somebody on the Ops side that usually helps devs fixing things here and there, in those cases I'd rather them say "X is broken" and then I ask the question to Claude with all the context I have.
Probably the best solution currently is a shared skill with at least some curated context.
I think that's the key. Generally people would rather not receive slop because the receiver has no idea how much thought the sender invested in the communication.
In your example, the more context the better. I think there's an interesting nuance there.
That's an interesting thought. The message can have metadata that says the sender's spent 1/5/10/60/120 minutes or some other metric of how much thinking over the communication happened. Just need a way to monitor people's thoughts and digitize them to make that happen.
Really? How does Claude gather that context?
"read it all, yes even the bullets. especially the bullets"
if you read one thing from a large wall of text, its gonna be the bullet points, right? thats a big part of what they're for?
"It is the conversational equivalent of forwarding the email."
this is a terrible metaphor. it seems to rely on the idea you would be mad if you sent an email to someone and they forwarded to someone else? but thats useful, theyre literally sending it to someone who is presumably better placed to help you, or raising it to someone more important because they think what youre saying is important
Interesting to note the page also ends with "written by a human, on purpose"
Hypocritical to say the least, given the message.
And the result isn't even very angry at all. It's like mildly peeved internal company communication (also in direct violation of "don't send this to your manager")
DS9 Garak "especially the lies" reference maybe?
But the point is. They had search, so why didn't they think to do the search? They had the same tools as I did. And yet regularly they couldn't think of the answer. I still deal with this with AI today. When you ask a question, maybe you're asking for the interpretation of the question by the person on the other side. And it's that interpretation that goes to the LLM. Or otherwise some filter of how that person thinks about the question differently than you do.
This is exactly what I have been feeling in response to this person. They are not contributing. They are creating work for others by pasting every possible problem they can find, most of which are out of scope or context, and letting the requester sort through them which takes hours if you take it seriously.
Some people do and implement everything he asks. They are going way outside the scope of their ticket and fixing every problem in every file they touch. It is chaotic and not good for the codebase because a lot of the problems are repo wide and should not be fixed in isolation.
He doesn't seem to understand why this might bother people or why it takes them so long to respond. He suggested just pulling the comment into Cursor and just asking Cursor to respond...
At that point we are just straight up vibe coding with no human in the loop.
That being said, Cursor's bug bot does a way better job reviewing, and people just ignore it when it asks for something out of scope because it's not a colleague claiming their code is broken.
You're gonna need a stronger language. Why do you think people love AI? If I have to think and god forbid read the response I might as well live in the woods or something
Unique human prompt + AI output which is useful and does a good job expanding on the prompt topic and which when pasted saves people the time of having to go prompt AI on the same topic (fully reviewed by a person before sharing it, to ensure the content has relevance)
Would be interesting if someone said “I spent $2.50 using llm-council with the three top SOTA models and think this reply makes sense: {paste}”
(But better “not sure, though after spending a few bucks on model APIs, perhaps {human-written analysis} is in the right direction”)
Also like you, I did think on the angry version “they have the same AI you do” isn’t likely to be right in the consumer space since their AI is ChatGPT (free version?!) and yours is Claude or something.
There's responsible AI use (which I think you - and I, and many people here) do, and the "I don't care, I've outsourced my brain to OpenAI" type of people.
Over time, it was impressive to see how much the output of the same prompt would differ between us, and it seems to be heavily influenced by the role of the user. I.e. answers coming from the agent of a Data Engineer, a Backend Engineer and a Domain Researcher would not be the same at all. Some of us use harnessing tools, some not, but regardless it we saw differences.
So, for example, when a backend engineer would send a question to a data engineer, there was *some* added value even when it was a lazy copy & paste.
Dont be a meat proxy! simple
DO NOT FUCKING PASTE AI RESPONSES TO ME, EVER, PERIOD.
When someone tells me they "talked to Claude" they sound retarded. Just tell me you looked into it, and I fucking swear to god if you just took what Claude said verbatim and do not understand the problem then you are a cunt and I will stop working with you.
When someone pastes LLM output in chat I completely ignore it. I will just continue the conversation as if they said nothing and silently mark them as cretinous in my mind.
This is not up for debate, you will talk to me in short well formed sentences and get to the fucking point or you will fuck off
This is really useful, I wish more people would understand this: you don't have to have an opinion on everything. In fact, you probably shouldn't have an opinion on most things.
My own take on the AI issue: https://blog.gpkb.org/posts/just-send-me-the-prompt/
Especially today, I will prefer your slightly funny English to something that feels like AI.
And personally I do Support for people around the world and I often ask people to write in their native language.
Then I can translate myself and if the default ai translation gets something wrong I can add necessary context to improve it - which I can't really do if the only thing I get is the bad ai translation.
Der skal kom et tid hvor du skal tale på en sprog på dit kontor. Uden hjælp. Du har bruge for at øve dig, og folk er alligevel pænere end du tror.
(this being written in a foreign language I am learning is part of the point)
And in my experience, us Brits, and USA folk, we tend to be quite understanding of broken English
I like to think it helped, but likely what helped was that nobody seems to use Deep Research anymore, haha.
idk about that
[edit] to extend the connections The charm of a messaging board like this is bringing "join attention" to a topic, not just sharing separate monologs.
And also, always wondering if something was written by a human or statistically generated could be seen as Epistemic Hypervigilance, leading to stress, and loss of epistemic trust. This could reduces opportunities for taking on new information of feedback, and cause rigidity and isolation.
and i detest ai slop
so my solution is to speak combined with an ai cleanup like macwhisper or wispr flow of all the uhs and ahs and repetitions or rephrasings etc
you can even use ai to pretend a conversation or interview style
then i have stuff to edit
boom
Almost certainly written by AI
It also ends with "written by a human, on purpose"
Disagreed. Bad writing from a chatbot beats worse writing from its user every time - regardless of length.
One reason we have so much bot slop is the attractiveness of bad-writing bots to the many people whose writing is even worse.