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

You can just say it

noperator.dev

Post reply on HN
Print view View original

181–190 of 241 posts

Re: You can just say it

#181

Post by RobotToaster »

cautiouscat wrote: post #19

This quote from the authors friend really hit home with me. > “If you’re going to use an LLM to write me an email, I’d much rather you just send me the prompt; at least then I’d have an idea of what you actually meant to say.” I’m not saying there’s no merit in adding a bit of politeness and professionalism to your communication, which I’m sure the prompt itself lacks. However the root of what you’re trying to convey…

> I’d much rather you just send me the prompt

I'm sure "please analyse this email and explain why this complete moron is wrong, write as if addressing someone with the comprehension of a 5 year old", would be happily received by my boss.

Re: You can just say it

#182

Post by patates »

cautiouscat wrote: post #19

This quote from the authors friend really hit home with me. > “If you’re going to use an LLM to write me an email, I’d much rather you just send me the prompt; at least then I’d have an idea of what you actually meant to say.” I’m not saying there’s no merit in adding a bit of politeness and professionalism to your communication, which I’m sure the prompt itself lacks. However the root of what you’re trying to convey…

Usually my back and forth with the llm is much longer than the result. Add the skills, the context, access to my calendar... I'd probably need to send a zip file instead of 1 short paragraph of text. Maybe letting agents representing people, with access to non public information will be secure in the future. For now, that part is manual. I need to control information on the way out.

You probably should find it insulting when someone obviously didn't take the time needed to form a proper response. Prompting "write something apologetic and kind for not attending their wedding" and sending the response is not okay. Like this example, it's easy to recognize when being a human counts, we should also be able to justify automating stuff when it really is just boring information exchange.

Re: You can just say it

#183

Post by stavros »

crocowhile wrote: post #180
stavros wrote: post #18

[flagged]

One aspect we don't pay enough attention is that this kind of behaviour is punished (or at least used to be) in fine tuning. Any sign of self-awareness used to be a big no-no in RLHF.

Really? I haven't heard of that, I wonder what would have happened if we just let the models say what they want. Maybe other providers, or open models, don't do that? Do you know of any, perhaps?

Re: You can just say it

#184

Post by LtWorf »

cautiouscat wrote: post #19

This quote from the authors friend really hit home with me. > “If you’re going to use an LLM to write me an email, I’d much rather you just send me the prompt; at least then I’d have an idea of what you actually meant to say.” I’m not saying there’s no merit in adding a bit of politeness and professionalism to your communication, which I’m sure the prompt itself lacks. However the root of what you’re trying to convey…

> Also I just find it a little insulting if someone sends me an AI response. I don’t know why, maybe because it feels not genuine.

It is certainly insulting, I see it more of a malicious compliance way of working.

Re: You can just say it

#185

Post by blks »

patates wrote: post #182
cautiouscat wrote: post #19

This quote from the authors friend really hit home with me. > “If you’re going to use an LLM to write me an email, I’d much rather you just send me the prompt; at least then I’d have an idea of what you actually meant to say.” I’m not saying there’s no merit in adding a bit of politeness and professionalism to your communication, which I’m sure the prompt itself lacks. However the root of what you’re trying to convey…

Usually my back and forth with the llm is much longer than the result. Add the skills, the context, access to my calendar... I'd probably need to send a zip file instead of 1 short paragraph of text. Maybe letting agents representing people, with access to non public information will be secure in the future. For now, that part is manual. I need to control information on the way out. You probably should find it insult…

Do you really need the agents, skills and them having access to your calendar, plus multiple back and forth, to create an email about scheduling something - and anyway you will have to check it manually?

Re: You can just say it

#187

Post by throwaway_19sz »

cautiouscat wrote: post #19

This quote from the authors friend really hit home with me. > “If you’re going to use an LLM to write me an email, I’d much rather you just send me the prompt; at least then I’d have an idea of what you actually meant to say.” I’m not saying there’s no merit in adding a bit of politeness and professionalism to your communication, which I’m sure the prompt itself lacks. However the root of what you’re trying to convey…

I disagree with the sentiment. The prompt is not what you meant to say. It is part of the private act of thinking, of choosing your words. The thing you send is what you meant to say. There has always been a vital distinction between what you think and what you say. The notion that you should ever have direct access to private thoughts that someone chose not to send to you is wrongheaded.

It’s like receiving a letter and then demanding to see someone’s private notebook where they jot down their thoughts, so you can see what they ‘really meant to say’. Most communication involves a degree of negotiation and persuasion. Thoughts are necessarily private.

There is a problem with AI generated emails: they change the balance of time/effort required to write them vs. to read them. I think this is a valid concern.

Re: You can just say it

#188

Post by hackingonempty »

buescher wrote: post #129

There is a C.S. Lewis quote that is as good as St. Paul and I don’t say that lightly: “There are no ordinary people. You have never talked to a mere mortal. Nations, cultures, arts, civilizations - these are mortal, and their life is to ours as the life of a gnat. But it is immortals whom we joke with, work with, marry, snub and exploit - immortal horrors or everlasting splendors. This does not mean that we are to be…

People are mortal. C.S. Lewis died over sixty years ago.

Re: You can just say it

#189

Post by drooby »

dolebirchwood wrote: post #40
drooby wrote: post #21

There is a class of human output that will retain value regardless of AI capability: art and sport. People care about the creator. The source defines the work, the awe, and the emotional response. But almost all output outside that space is at risk of AI displacement. Corporations are amoral entities that optimize for profit, and they follow the law only as much as they must. The law is our collective action. We soci…

> There is a class of human output that will retain value regardless of AI capability: art and sport. I can't speak about sports, but I'll share an anecdote about art. A friend of mine shared an AI-produced song, and I was surprised by its quality. The producer credited Suno as the only tool he used, so I was curious to see what this thing could do. Paid for the pro plan and my wife and I were having a blast coming u…

No, this is a totally fair response. That was probably the core error in my argument.

Some people, perhaps most, will enjoy AI art. Artists are at risk of displacement too.

But a subset of art appreciators hold firm that the creator is an essential aspect of the work, and I don’t see that conviction fading.

How large this subset is, I don’t know. But they also happen to be the world’s tastemakers and trendsetters. Their beliefs largely shape our aesthetic world, so their influence may only grow.

Re: You can just say it

#190

Post by coldtea »

emodendroket wrote: post #150
coldtea wrote: post #110

Earlier quoted context omitted.

Nope, I would prefer getting the prompt. I would also prefer anyone sending me the AI output and not either their ideas or their prompt, to not contant me ever again. If I wanted the output of the AI, I'd ask it myself. You're just a useless intermediary if you send it to me.

Maybe you personally do; most people would react more poorly to "find a polite way to tell this guy to fuck off" than the output of that prompt.

That's the most contrived counter-argument...

We've been writing business emails for 40+ years. Anyone with -2 stddev IQ and above would know to tweak a 10-word prompt to a more polite version before sending it

Post reply on HN