Talk like Paul Dirac – fewer words is better | Hacker News Reader

Talk like Paul Dirac – fewer words is better

13 pointsasen20 comments

This is the entire contents of my home dir AGENTS.md file now.

Does it help reduce the slop you have to read for you the same way it feels like it does it for me?

I actually take this advice in real life. I don’t talk unless really needed. There are exceptions like to my kid, but that’s the general principle to non family/friend members.

I always liked the picture of dirac and feynmann, and dirac looks so bored

Dirac would never make that less vs fewer mistake.

Agreed, thanks! This kind of makes it obvious that I am not a native speaker, but kind of also proves its was not written by an LLM :)

Edit: fixed now: less words -> fewer words

FYI it's a somewhat regional or (in the UK) class stratified grammar distinction.

While nobody would say "fewer sand", "less" is in practice often used by native English speakers for both count and non-count nouns so it's not really wrong so much as it is revealing.

> is in practice often used by native English speakers for both count and non-count nouns

Alternative explanation: native speakers are wrong sometimes.

It really boils down to:

- Less + uncountable noun (money, energy, code, sand)

- fewer + countable noun (trees, cars, grains, volts, coins)

If instead we prefer to attribute it to class and say using the correct or wrong way is a class signifier and that both are correct, and that language depends on usage and there are no grammar rules really but only consensus, we can also do that. But then "Why waste time say lot word when few word do trick?".

I prefer the first explanation.

P.S. Same with "if I were" turning into "if I was". I guess usage turned that one, and that is fine too. I make that mistake often.

In Spanish these guys (https://www.rae.es/duda-linguistica/el-nombre-de-la-y-es-i-g...) also officially changed the name of "y" (i griega) to "ye". The argument: it is easier for new speakers. I will say "i griega" forever I am afraid.

There is no English Grammar Institute to tell us what is right and wrong, so English grammar is necessarily descriptive and not prescriptive.

It may annoy you, and you may be convinced that you are right and others are "wrong" but if a substantial body of people use English in a way that you dislike then it's just tough shit I'm afraid.

> But then "Why waste time say lot word when few word do trick?".

Because nobody actually talks like that, that's why.

You don't speak Elizabethan English, or Regency English, or late Saxon, or Old English, but you presumably don't think those are "wrong" - why do you think Estuary English is wrong; could it be gasp because you're in a different linguistic group? /me clutches pearls...

I am not annoyed, I choose one side over the other in this debate https://en.wikipedia.org/wiki/Fewer_versus_less

You always have authorities like dictionaries and English usage references. There are some supporting each side of this debate in the link above.

> if a substantial body of people use English in a way that you dislike then it's just tough shit I'm afraid

There is no need for that language. hn is supposed to be a place of civil (and playful) discussion. I also already anticipated that take in my post.

> If instead we prefer to attribute it to class and say using the correct or wrong way is a class signifier and that both are correct, and that language depends on usage and there are no grammar rules really but only consensus, we can also do that

> You don't speak Elizabethan English, or Regency English, or late Saxon, or Old English, but you presumably don't think those are "wrong"

Because nobody actually talks like that, that's why. Joking. You introduced the time dimension, which complicates the comparison. If somebody claimed those are all correct ways of speaking in modern English, and only class signifiers, in that context, I would say they are wrong.

In general I dislike this nihilist "truth does not exist" nobody-is-wrong take. That is why I prefer the simple rule with countable and uncountable without the class excuse. Ultimately both takes are valid, but I find the second one too nihilist for my taste.

If people one day start saying "me thinks this good" you might find yourself changing sides arguing that truth does, in fact, exist.

Who said you were annoyed? I'm just pointing out that English is a democratic language, has no centralised institute defining correctness, and drawing borders around areas of it is completely pointless.

You're entitled to believe that some grammatical forms are "wrong" and I'm entitled to have no respect for that opinion.

I, for example, strongly dislike the change of meaning of "disinterested" to mean "uninterested", but have no illusion that there's some absolute truth of His Majesty's Royal English Language to prop up my ego.

In practice, where such institutes do exist, they trail after the language bringing the rules into alignment with it, or are utterly ignored by all but the most officious.

> Who said you were annoyed?

You did. Quote "It may annoy you,". But nevermind.

> You're entitled to believe that some grammatical forms are "wrong" and I'm entitled to have no respect for that opinion.

I think you also believe this, we only disagree in which grammatical forms. Or are you arguing that "Why waste time say lot word when few word do trick?" is grammatically correct?

If you are, then it is consistent with your popular-makes-correct approach as long as people say it. Whatever mistake stops being a mistake if repeated by enough people; if not, then we agree and only disagree on where the line is.

No bad feelings anyway. Nice chat.

Replying to myself as we reached the thread limit. Slightly bad form, but I doubt there are many (any) others listening in the thread:

>> You did. Quote "It may annoy you,". But nevermind.

You misinterpret. It may annoy you. It may not. A cat may look at a king.

>> I think you also believe this, we only disagree in which grammatical forms. Or are you arguing that "Why waste time say lot word when few word do trick?" is grammatically correct?

I'm arguing that the question is meaningless. Some will sound correct to my ear. Some will not. Some will sound correct to nobody. None of them are "wrong" because there is no authority beyond convention to dictate which is "correct" - and conventions differ between different users of language.

I would never say "on accident" but it would be fatuous to say that it was "wrong" just because I don't use it when millions do.

> ...only disagree on where the line is.

I don't really agree that there's a line. If one person uses an unconventional construction is it wrong? Not really, though they may be hard to understand. Or not. Half the art of great usage of the language is coming up with unconventional forms.

> No bad feelings anyway. Nice chat.

None felt, none intended. Likewise.

You want people to talk to you the way you listen. So does everyone else, and most of them do not listen the way you do.

this is an instruction for LLM, not for people

LLMs are what you get when you put people through a stack of filters.

    - Only Use Attempto Controlled English
    - Do not make any sentence in negative phrasing

Thanks. And maybe I am wrong, but I feel that Paul Dirac should be better represented in the weights than Attempto Controlled English, which sounds niche to me - or at least - I hear it for the first time.

Easy for anyone to try out themselves, and my post is only half a joke - it actually works. For me, at least :)

fun thing is that of course it will forget it in a long session and spit some too long text. but just typing `dirac` makes it recall the instruction and shorten it

Would Dirac get a job these days?

The reason i believe is good is because with very few tokens you encode two properties, for which Paul Dirac is most famous for.

* a great scientist (which hopefully encourages researching and verifying answers)

* a person who doesn't like to use many words at all

The later hopefully compensates the apparent "output-prose-greediness" most models seem to have. No idea if that "token greedines" (or slop) is a result from the companies business models or inherent for the models and their training :/

To me adding 'tldr' at beginning or end of the prompt whenever I need is enough. Sometimes I want more explanatory responses.

Reply on news.ycombinator.com