Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

Don't paste the AI, please

dontpastetheai.com

Post reply on HN
Print view View original

391–400 of 632 posts

Re: Don't paste the AI, please

#391

Post by andy99 »

john_strinlai wrote: post #364
mhaberl wrote: post #353

Earlier quoted context omitted.

> Back in the day I learned the hard way that sending a long reply to an email just ensures the other side won't read it. You can't assume that you dealt with their request effectively that way Then I guess you didn't deal with much of the empty-headed-managment type much. I learned a different lesson: Write a long email that took time to reason and write, precise and complete text. You get a short reply that is a re…

> This is true 100% I would even say: "Never reply on anything instantly that is not an absolute emergency, ever" you can shorten this to "never reply instantly", because an "absolute emergency" will never be communicated by email.

What is the problem with replying instantly? If you can give a reply immediately why wouldn’t you? If it’s low priority work that takes time, sure, but a typical yes/no, I’m available at 5, whatever, why not just send it?

If you’ve already read the email it’s less efficient to come back to it later

Re: Don't paste the AI, please

#393

Post by selcuka »

throwforfeds wrote: post #373
disillusioned wrote: post #17

Heh. Just got done writing (by hand!) a Principles of AI Use document for my (ironically) AI enablement firm, the first of which is: 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 your…

I was having a Slack convo with a dev on another team a month ago as I had a question about that system's support for OTEL, and it became clear really quick that I was just having a convo with an LLM proxied through this person. It was wild, as it had never even occurred to me to just copy/paste out of an LLM while having a convo with someone else.

Those people exist.

What is worse is that they don't even bother to provide the correct context to the model, or even use the same model to answer your questions. So, for example, they submit a PR using an LLM, and when you ask them to justify an engineering decision, another LLM responds with a completely nonsensical reply because it doesn't have the same context as the first one.

Re: Don't paste the AI, please

#395

Post by rho4 »

akie wrote: post #14

Did they really just say "genuinely useful" in a post decrying the blind copy-pasting of AI text? (it's a strong Claude indicator)

Was going to say the same but then decided to search first if someone beat me to it. Sigh.

Re: Don't paste the AI, please

#396

Post by randcraw »

dr_dshiv wrote: post #44
seer wrote: post #35

I’m not convinced tbh, a lot of my colleagues messages are “x broken” or “I do y” … no context whatsoever, and then I have to coax their context for making these decisions. 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…

Points to the future where my bots talk to your bots. I think that’s healthy. 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.

> Points to the future where my bots talk to your bots. I think that’s healthy.

I can't imagine why. You have become a robot. You've automated yourself out of existence. And due to your consistently mindless replies, everyone now knows there's no point in talking to you ever again.

How is that healthy?

Re: Don't paste the AI, please

#397

Post by john_strinlai »

andy99 wrote: post #391
john_strinlai wrote: post #364

Earlier quoted context omitted.

> This is true 100% I would even say: "Never reply on anything instantly that is not an absolute emergency, ever" you can shorten this to "never reply instantly", because an "absolute emergency" will never be communicated by email.

What is the problem with replying instantly? If you can give a reply immediately why wouldn’t you? If it’s low priority work that takes time, sure, but a typical yes/no, I’m available at 5, whatever, why not just send it? If you’ve already read the email it’s less efficient to come back to it later

i'm not a strict adherent to the rule, your question would be better aimed at jillesvangurp or mhaberl.

mainly i just wanted to stress that nothing in an email inbox is an "absolute emergency".

Re: Don't paste the AI, please

#398

Post by bluGill »

ImPostingOnHN wrote: post #332
jillesvangurp wrote: post #308

The complaint here is about lazy answers. But what about all the lazy questions? What's the equivalent of "Google it yourself" these days? When you ask something of somebody, the expectation of the other side to drop everything and do work for you isn't always appropriate/balanced/appreciated. The underlying problem here is that communication is hard; especially if it's not face to face. People can't read your mind o…

If you work for a company of more than 1 person, then helping and developing and mentoring your colleagues is part of your job, and a more important one than telling them to rtfm so you can spend those few minutes getting your own thing done. A company isn't just a bunch of people isolating themselves and doing their best to not talk to each other.

I always tell people "Here is the documentation, please tell me what is hard to understand so I can fix it". When someone is new on my team I tell them "here is our team documentation, your first task is to fix it so that the next person can follow the directions correctly".

That is I make the conversation not about them reading the manual, but about making it worth reading. There is a large amount of really bad documentation out there.

Re: Don't paste the AI, please

#399

Post by bluecheese452 »

NateEag wrote: post #363
Cthulhu_ wrote: post #173

Earlier quoted context omitted.

You'd think two decades of StackOverflow would've teached people how to ask a good question.

Alas, what it taught people was to describe others who want to help them ask better questions as "gatekeepers". Maybe SO really is full of rude, condescending gatekeepers - I haven't asked questions there much. I haven't personally seen much evidence of it, though, despite decades of winding up there when searching for programming information.

If you haven’t asked questions how would you know? A question that gets incorrectly closed as a duplicate would never get seen by you.

Re: Don't paste the AI, please

#400

Post by p_j_w »

rpdillon wrote: post #382
Forgeties79 wrote: post #319

Earlier quoted context omitted.

> what’s the equivalent of “google it yourself” these days? Do you actually say that to people? Edit: i’ve hit the comment limit per given time, but all I have to say is “what have you found so far?” And “Google it yourself” are radically different responses man. The former is far more reasonable, it shows you are willing to be helpful and is a productive question. The other is just rude and implies your time is too…

People are lazy as hell, and I've noticed it's getting worse. My old team called this "remote brain execution" (because we work with Bazel and they have something called RBE) where folks would just drop questions in Slack and just ask the team to solve it for them. We were taken aback by how little work people would do before doing this. We developed the phrase: "What have you tried so far?" to try and counteract thi…

I try to give people a little leeway here, even if I get annoyed in the moment. I know that I myself have dropped a question in chat and continued to look elsewhere for the answer. It’s always a good idea to see if someone else has a quick answer to avoid spinning your wheels for hours looking in the wrong direction.
Post reply on HN