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

591–600 of 632 posts

Re: Don't paste the AI, please

#591

Post by chrisweekly »

john_strinlai wrote: post #564
chrisweekly wrote: post #562

Earlier quoted context omitted.

(Replying to parent and GP) I wasn't suggesting an IM system should be the source of truth for long-form documentation. But searching Slack works better than searching email you weren't cc'd on. Virtually anything is better than email for many essential aspects of collaboration. Want to add someone to the mailing list and loop them in? How many prior emails will you forward to them? Someone replies to one of several…

we have polar opposite opinions on email and slack/teams/discord! im not sure i am even understanding the issues you brought up about email correctly. may i ask what age bracket or generation you are? only if you're comfortable sharing, of course. im in my 60s. and im curious if our difference of opinion here is a product of what technologies were/are available during the start & prime of our careers. i very well mig…

Thanks for considering possible reasons for disagreement. I'd like to understand it, too. FWIW, I'm about to turn 52. Been working in tech since the late 1990s. Remote more than not. Email is great for certain specific things. But for multiuser async collaboration in the workplace, surely you've encountered problems like I have, no? Email conversations -- especially if they're long and/or include a lengthy recipient list -- are inherently prone to critical failure, completely decohering as _both_ the recipient list(s) _and_ the topic(s) under discussion can fragment from the very first of N replies, making it impossible to resolve anything conclusively or to know what's been communicated to whom.

Re: Don't paste the AI, please

#592

Post by chrisweekly »

prepend wrote: post #571
chrisweekly wrote: post #562

Earlier quoted context omitted.

(Replying to parent and GP) I wasn't suggesting an IM system should be the source of truth for long-form documentation. But searching Slack works better than searching email you weren't cc'd on. Virtually anything is better than email for many essential aspects of collaboration. Want to add someone to the mailing list and loop them in? How many prior emails will you forward to them? Someone replies to one of several…

I use a git-generated static site that has good search, so if people want to find stuff before asking that’s the go-to. Otherwise, I can search email quite effectively. And oddly, its one of the few things Office Copilot is goos at. I don’t email is a collaboration tool. It’s an information sharing tool and maybe workflow. Just today I had to email out to like 20 people a data call with a couple paragraphs of instruc…

> "I don’t email is a collaboration tool"

That's almost the entirety of my point. Sure, email works well for simple, unidirectional / broadcast comms. But for async collaboration involving multiple recipients and any kind of back and forth, it's inherently problematic.

Re: Don't paste the AI, please

#593

Post by chrisweekly »

BeetleB wrote: post #567
chrisweekly wrote: post #563

Earlier quoted context omitted.

How do you search emails you weren't cc'd on?

If it has to be information stored in depth, then sure a KB/wiki is better. IME, the majority of long emails should not be persisted in such places, because they contain a fair amount of errors. One could say that any long email thread should be eventually synthesized in the KB/wiki after the conversation has wound down. And Slack/Teams? No way. If I need to write something long in response to a Slack IM, and email i…

I think we're on roughly the same page. Long emails are problematic. Realtime meetings or (possibly but not necessarily near-realtime) chats in a dedicated channel can and do solve email's problems.

Re: Don't paste the AI, please

#594

Post by andrewflnr »

the_af wrote: post #561
andrewflnr wrote: post #462

Earlier quoted context omitted.

This defines "communicating effectively" in a way that it can't possibly cover a complex topic. Sometimes you need to communicate complex topics, so this definition is a failure. The problem remains that people refuse to do the reading required for their job.

> This defines "communicating effectively" in a way that it can't possibly cover a complex topic [...] so this definition is a failure. Indeed, I don't think email can be reliably used to convey complex topics. > The problem remains that people refuse to do the reading required for their job. Communicating effectively means accepting common flaws of people who are unlikely to change, and delivering your message in th…

I don't think these people read the official documents either, though.

Adjusting communication to the audience is a good guiding principle, but not an absolute. There comes a point where no attempt at communication works for a given audience. If the communication must happen nevertheless, then the audience must change, whether through training or replacement.

Re: Don't paste the AI, please

#595

Post by keithnz »

keithnz wrote: post #274

I disagree strongly. Nearly every time this comes up it seems people are not doing a good job giving their AI context. My AI environment is REALLY context aware based on a whole bunch of things I have access to that others don't. When my AI respond to a question it is full of information the person asking the question just didn't have access to. You can also train your AI not to give a wall of text but to give very c…

down voting this is silly, just shows how badly people are buying into this. It is misguided. On the other side of things I guess it's good not everyone is working out how to be super productive with AI.

Re: Don't paste the AI, please

#596

Post by foltik »

bazmattaz wrote: post #543
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…

Is the problem that the response sounds like AI? Or the response is incorrect? Or too verbose? Or a mix of all three or something else? What if the response was perfect and sounded exactly like your colleague. Would you care if it was AI generated then? I think there could be a world where a colleague could just ask its (finely tuned) AI tool of choice to respond for it and colleagues would hardly notice as the outpu…

If all your colleague does is generate a “response” in a specific writing style based on some context, there’s no reason to talk to them at all. The good ones have some novel human insight that can’t be approximated by a slop generator.

And if you really want to record all your work and project context somewhere, just let people ... look at that directly? Or summarize and query it with their own LLM if they want to?

Re: Don't paste the AI, please

#597

Post by bonoboTP »

dnemmers wrote: post #315
bonoboTP wrote: post #246

Earlier quoted context omitted.

That's a good use for AI. Type loosely and ask it to fix up the spelling, capitalization and punctuation.

Fixing spelling, capitalization, and punctuation...that's just a spell checker, no fancy LLM needed.

It is needed. Sometimes the semantics matter.

Re: Don't paste the AI, please

#598

Post by bonoboTP »

anotherevan wrote: post #587
bonoboTP wrote: post #246

Earlier quoted context omitted.

That's a good use for AI. Type loosely and ask it to fix up the spelling, capitalization and punctuation.

Except that it will get it wrong infrequently but often enough that you should really proof-read the result properly. All of which you end up taking more time than if you wrote proper if the first case.

No, it takes less time. This is the same kind of take as the teacher's "writing a cheat sheet is so much effort that you might as well spend it to learn the material". Lol, no it takes less time, that's why people do it.

Re: Don't paste the AI, please

#599

Post by wasdly »

darkwater wrote: post #175
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…

Good luck with that, I hope you are in a better org that I am in that regard. I wanted to do that, proposed it in a directors' meeting and got push back from directors already using the Slack MCP to post normal conversations on their behalf (90% of time, pure slop). What you wrote just seems common sense to me, and I'm hopeful it will emerge as such given enough time.

Convincing some of the older generations not to blindly paste LLM output might be a lost cause. I’m sure we’ll be teaching LLM etiquette to Gen Alpha/Beta, if that isn’t already starting to happen in schools.
Post reply on HN