C++ in middle english

[Mut...@dastardlyhq.com]

A bit off topic but thought this might be appreciated. I asked chatGPT to
describe C++ as middle english poem. This AI is incredible:

In the realme of programmynge, C++ doth resideth,
A langage of myghte, its secrets it provideth.
With intrikat syntax, lik a maze profounde,
It chaunges the wey ofe programeers, yf yow wolde.

Objects, lik knyghtes, withinne classes doth resyde,
Encapsulatynge data ande methodes, they abyde.
Classes, lik castels, bestowe noble myghte,
Inheritance passeth lineage, shynynge bryghte.

Polymorphisme, a marvelouse art to use,
Transfigureth objects, takynge dyvers forme and hues.
Functiones, lik minstrels, her songes they do synge,
With parametres ande returnes, her melodyes sprynge.

Yet, taketh heed, noble programmer, for trappes may appeere,
Memory lekes ande faultes, yf yow art yclept afeared.
Pointers ande referencys, thy guides in this affray,
Shal guide thee to memory managynge in the righte way.

So, embarketh on this journe, thou valyaunt coder,
With knowledge ande skill, thine endeavor shalodour.
May this Middle English spelinge, inspirynge thyne queste,
Illuminate C++'s misteries ande bringe thee the beste.

[Pavel]

WOW. Just WOW. The back-handed compliment in the last verse is my
favorite. Thanks!

[Mut...@dastardlyhq.com]

On Wed, 24 May 2023 21:47:19 -0400
Pavel <pauldont...@removeyourself.dontspam.yahoo> wrote:

>Mut...@dastardlyhq.com wrote:
>> So, embarketh on this journe, thou valyaunt coder,
>> With knowledge ande skill, thine endeavor shalodour.
>> May this Middle English spelinge, inspirynge thyne queste,
>> Illuminate C++'s misteries ande bringe thee the beste.
>>
>>
>>
>WOW. Just WOW. The back-handed compliment in the last verse is my
>favorite. Thanks!

Personally I find its abilities rather concerning since they're only
going to improve exponentially.

[Michael S]

Does it really resembles Middle English or just an arbitrary funny misspelling?

[David Brown]

It will improve in some ways, and not in others. It can always get
faster and more flexible (though not "exponentially" so). But current
AI bots suffer from several critical flaws, and it is not easy to see
how they can be fixed. They base their knowledge on what they find
online, but have no way to judge the veracity of the sources, they have
no concept of error margins and reliability of the information they have
processed or produce, no understanding of ethics or appropriateness
(beyond a few simple pattern-matching rules rushed in to cut down on the
worst abuses).

This all means it has no idea when it is telling the truth, and when it
is lying or simply making things up. When making this poem, it has no
idea if the sources it used for the language were real Middle English,
modernised spelling of Middle English, made up pretend Middle English,
sources from 1066, sources from 1500, or whatever. It doesn't really
matter for a fun sample like this - it looks very impressive, though it
would make even the most amateur Chaucer fan cringe. But until there
are major fundamental changes, the use of such AI tools is severely
limited because they can't be trusted to have any basis in truth or reality.

Still, they can cheat in exams, write speeches for politicians and work
as journalists for the Daily Mail and Fox news, and no one will notice.

[Mut...@dastardlyhq.com]

On Thu, 25 May 2023 06:48:34 -0700 (PDT)
Michael S <already...@yahoo.com> wrote:
>On Thursday, May 25, 2023 at 12:06:14=E2=80=AFPM UTC+3, Mut...@dastardlyhq.=
>com wrote:
>> On Wed, 24 May 2023 21:47:19 -0400=20
>> Pavel <pauldont...@removeyourself.dontspam.yahoo> wrote:
>> >Mut...@dastardlyhq.com wrote:=20
>> >> So, embarketh on this journe, thou valyaunt coder,=20
>> >> With knowledge ande skill, thine endeavor shalodour.=20
>> >> May this Middle English spelinge, inspirynge thyne queste,=20
>> >> Illuminate C++'s misteries ande bringe thee the beste.=20
>> >>=20
>> >>=20
>> >>=20
>> >WOW. Just WOW. The back-handed compliment in the last verse is my=20
>> >favorite. Thanks!
>> Personally I find its abilities rather concerning since they're only=20
>> going to improve exponentially.
>
>Does it really resembles Middle English or just an arbitrary funny misspell=
>ing?

Better than I could do and I like to think it couldn't just conjure up these
sorts of spellings but did learn them somewhere.

[Mut...@dastardlyhq.com]

On Thu, 25 May 2023 16:17:30 +0200
David Brown <david...@hesbynett.no> wrote:
>On 25/05/2023 11:04, Mut...@dastardlyhq.com wrote:
>> On Wed, 24 May 2023 21:47:19 -0400
>> Pavel <pauldont...@removeyourself.dontspam.yahoo> wrote:
>>> Mut...@dastardlyhq.com wrote:
>>>> So, embarketh on this journe, thou valyaunt coder,
>>>> With knowledge ande skill, thine endeavor shalodour.
>>>> May this Middle English spelinge, inspirynge thyne queste,
>>>> Illuminate C++'s misteries ande bringe thee the beste.
>>>>
>>>>
>>>>
>>> WOW. Just WOW. The back-handed compliment in the last verse is my
>>> favorite. Thanks!
>>
>> Personally I find its abilities rather concerning since they're only
>> going to improve exponentially.
>>
>
>It will improve in some ways, and not in others. It can always get
>faster and more flexible (though not "exponentially" so). But current
>AI bots suffer from several critical flaws, and it is not easy to see
>how they can be fixed. They base their knowledge on what they find
>online, but have no way to judge the veracity of the sources, they have

Neither do humans frankly.

>no concept of error margins and reliability of the information they have
>processed or produce, no understanding of ethics or appropriateness
>(beyond a few simple pattern-matching rules rushed in to cut down on the
>worst abuses).

Neither do some humans. It doesn't mean they can't think. You're missing
the elephant in the room - this thing might not be concious but it is
thinking , its not a dumb stats based system like a markov model or similar.

>Still, they can cheat in exams, write speeches for politicians and work
>as journalists for the Daily Mail and Fox news, and no one will notice.

Only after they've worked their way up from writing for woke comics such as
The Guardian.

[David Brown]

On 25/05/2023 17:27, Mut...@dastardlyhq.com wrote:
> On Thu, 25 May 2023 16:17:30 +0200
> David Brown <david...@hesbynett.no> wrote:
>> On 25/05/2023 11:04, Mut...@dastardlyhq.com wrote:
>>> On Wed, 24 May 2023 21:47:19 -0400
>>> Pavel <pauldont...@removeyourself.dontspam.yahoo> wrote:
>>>> Mut...@dastardlyhq.com wrote:
>>>>> So, embarketh on this journe, thou valyaunt coder,
>>>>> With knowledge ande skill, thine endeavor shalodour.
>>>>> May this Middle English spelinge, inspirynge thyne queste,
>>>>> Illuminate C++'s misteries ande bringe thee the beste.
>>>>>
>>>>>
>>>>>
>>>> WOW. Just WOW. The back-handed compliment in the last verse is my
>>>> favorite. Thanks!
>>>
>>> Personally I find its abilities rather concerning since they're only
>>> going to improve exponentially.
>>>
>>
>> It will improve in some ways, and not in others. It can always get
>> faster and more flexible (though not "exponentially" so). But current
>> AI bots suffer from several critical flaws, and it is not easy to see
>> how they can be fixed. They base their knowledge on what they find
>> online, but have no way to judge the veracity of the sources, they have
>
> Neither do humans frankly.

True - but at least some of us can do a lot better job. No one is
immune to being fooled, and some people get fooled a /lot/, but these AI
systems have not yet reached the level of even the daftest flat-earthers
and "Q anon" followers.

>
>> no concept of error margins and reliability of the information they have
>> processed or produce, no understanding of ethics or appropriateness
>> (beyond a few simple pattern-matching rules rushed in to cut down on the
>> worst abuses).
>
> Neither do some humans. It doesn't mean they can't think. You're missing
> the elephant in the room - this thing might not be concious but it is
> thinking , its not a dumb stats based system like a markov model or similar.
>

I understand that, and I'm not missing anything.

The key, I think, is that humans go through many years of learning and
upbringing - these systems are like a child that has read thousands of
books, but has never been taught about trustworthy sources, never seen
anything bad happen, never made mistakes and been corrected. They are
highly knowledgeable and totally naïve. They need patient teachers and
"parents", working with them for many years at least, and no one is
willing to wait for that.

[David Brown]

It vaguely resembles Middle English - at least some of the funny
spellings are reasonable versions (transliterated into modern letters).
But it appears to have been done by making up a poem about C++ in modern
English (no mean feat in itself), then translating word for word where
the system could find a Middle English equivalent (with no regard for
context or consistency of time and place - Middle English spanned 400
years and was significantly different in different parts of the British
Isles). Some modern words have been modified by patterns common at the
time in an attempt at following Middle English grammar, others have not.

As a test of how authentic it is, I guess that most people in this group
can understand most of the poem. But if you look up some Chaucer or
other real Middle English poetry, I doubt you'll have much idea at all
about what it is saying - at least not without a lot of effort.

[Chris M. Thomasson]

Thou art Dead. They took our jobs! Grrrr...

[Mut...@dastardlyhq.com]

On Thu, 25 May 2023 20:49:28 +0200
David Brown <david...@hesbynett.no> wrote:

>On 25/05/2023 17:27, Mut...@dastardlyhq.com wrote:
>> Neither do some humans. It doesn't mean they can't think. You're missing
>> the elephant in the room - this thing might not be concious but it is
>> thinking , its not a dumb stats based system like a markov model or similar.
>>
>
>I understand that, and I'm not missing anything.
>
>The key, I think, is that humans go through many years of learning and
>upbringing - these systems are like a child that has read thousands of
>books, but has never been taught about trustworthy sources, never seen
>anything bad happen, never made mistakes and been corrected. They are
>highly knowledgeable and totally naïve. They need patient teachers and
>"parents", working with them for many years at least, and no one is
>willing to wait for that.

Sure, but like a lot of people you're missing the point. It doesn't matter
if the data its trained on is out of date or just pure rubbish, its the fact
that it somehow comprehends it and can make links between unrelated topics.

Plenty of very smart people in the past have argued about how many angels
can fit on the head of a pin because of the nonsense in religious story books,
that doesn't mean they're thick.

[Mut...@dastardlyhq.com]

On Thu, 25 May 2023 20:58:41 +0200
David Brown <david...@hesbynett.no> wrote:
>On 25/05/2023 15:48, Michael S wrote:
>> On Thursday, May 25, 2023 at 12:06:14 PM UTC+3, Mut...@dastardlyhq.com

>>>> WOW. Just WOW. The back-handed compliment in the last verse is my
>>>> favorite. Thanks!
>>> Personally I find its abilities rather concerning since they're only
>>> going to improve exponentially.
>>
>> Does it really resembles Middle English or just an arbitrary funny
>misspelling?
>
>It vaguely resembles Middle English - at least some of the funny
>spellings are reasonable versions (transliterated into modern letters).
>But it appears to have been done by making up a poem about C++ in modern
>English (no mean feat in itself), then translating word for word where
>the system could find a Middle English equivalent (with no regard for

The fact that it can do it at all is amazing to me.

>As a test of how authentic it is, I guess that most people in this group
>can understand most of the poem. But if you look up some Chaucer or
>other real Middle English poetry, I doubt you'll have much idea at all
>about what it is saying - at least not without a lot of effort.

Chaucer can be understandable , often its a modern word spelt in an old
way. Old English OTOH is a completely different language and is about as
comprehensible as German for any modern english speaker.

[David Brown]

On 26/05/2023 10:40, Mut...@dastardlyhq.com wrote:
> On Thu, 25 May 2023 20:49:28 +0200
> David Brown <david...@hesbynett.no> wrote:
>> On 25/05/2023 17:27, Mut...@dastardlyhq.com wrote:
>>> Neither do some humans. It doesn't mean they can't think. You're missing
>>> the elephant in the room - this thing might not be concious but it is
>>> thinking , its not a dumb stats based system like a markov model or similar.
>>>
>>
>> I understand that, and I'm not missing anything.
>>
>> The key, I think, is that humans go through many years of learning and
>> upbringing - these systems are like a child that has read thousands of
>> books, but has never been taught about trustworthy sources, never seen
>> anything bad happen, never made mistakes and been corrected. They are
>> highly knowledgeable and totally naïve. They need patient teachers and
>> "parents", working with them for many years at least, and no one is
>> willing to wait for that.
>
> Sure, but like a lot of people you're missing the point. It doesn't matter
> if the data its trained on is out of date or just pure rubbish, its the fact
> that it somehow comprehends it and can make links between unrelated topics.
>

Again - I am not missing anything. I understand what you are saying,
and I am impressed with what it is able to do. But precisely because it
is trained on data that is out of date, wrong, or deliberate
misinformation as much as current and correct information, the
conclusions it reaches and links it makes are often worthless, or worse
than useless (because they contain critical errors, but are given with
such confidence and mixed with true statements).

> Plenty of very smart people in the past have argued about how many angels
> can fit on the head of a pin because of the nonsense in religious story books,
> that doesn't mean they're thick.
>

The fact that human knowledge and human intelligence do not always match
up does not have any bearing on how useful chatbot-style AI currently
is, or how dangerous it can be, or where its future might lie. Humans
can get things wrong too, intentionally or unintentionally - that does
not make the AI systems less wrong.

[David Brown]

On 26/05/2023 10:42, Mut...@dastardlyhq.com wrote:
> On Thu, 25 May 2023 20:58:41 +0200
> David Brown <david...@hesbynett.no> wrote:
>> On 25/05/2023 15:48, Michael S wrote:
>>> On Thursday, May 25, 2023 at 12:06:14 PM UTC+3, Mut...@dastardlyhq.com
>>>>> WOW. Just WOW. The back-handed compliment in the last verse is my
>>>>> favorite. Thanks!
>>>> Personally I find its abilities rather concerning since they're only
>>>> going to improve exponentially.
>>>
>>> Does it really resembles Middle English or just an arbitrary funny
>> misspelling?
>>
>> It vaguely resembles Middle English - at least some of the funny
>> spellings are reasonable versions (transliterated into modern letters).
>> But it appears to have been done by making up a poem about C++ in modern
>> English (no mean feat in itself), then translating word for word where
>> the system could find a Middle English equivalent (with no regard for
>
> The fact that it can do it at all is amazing to me.

I fully agree.

>
>> As a test of how authentic it is, I guess that most people in this group
>> can understand most of the poem. But if you look up some Chaucer or
>> other real Middle English poetry, I doubt you'll have much idea at all
>> about what it is saying - at least not without a lot of effort.
>
> Chaucer can be understandable , often its a modern word spelt in an old
> way. Old English OTOH is a completely different language and is about as
> comprehensible as German for any modern english speaker.
>

Some Middle English is understandable, other parts are not - often the
context and culture differences are as much of a challenge as the words
themselves. But it is clear that Middle English is a precursor to
modern English, whereas Old English, or Anglo-Saxon, is very different.

[Mut...@dastardlyhq.com]

On Fri, 26 May 2023 15:30:58 +0200

Anglo Saxon is to modern english what latin is to french, italian, spanish
etc. Obviously related and with shared words but not generally intelligable
to a modern romance language speaker.

[Michael S]

On Thursday, May 25, 2023 at 9:58:57 PM UTC+3, David Brown wrote:
>
> As a test of how authentic it is, I guess that most people in this group
> can understand most of the poem. But if you look up some Chaucer or
> other real Middle English poetry, I doubt you'll have much idea at all
> about what it is saying - at least not without a lot of effort.

That's exactly what caused my suspicions. If non-native like myself
can understand it then it can't be too authentic.

[Keith Thompson]

The first line struck me as a likely grammatical error:

In the realme of programmynge, C++ doth resideth,

The modern English equivalent would be "... does resides", which should
be "does reside". I don't know the grammatical rules of Middle English,
but I would have expected "doth reside".

My own experiments with ChatGPT do not suggest that it "knows" enough to
generate correct Middle English. (On the other hand, Middle English
grammar was probably not at all strict, so maybe "doth resideth" would
be perfectly acceptable.)

--
Keith Thompson (The_Other_Keith) Keith.S.T...@gmail.com
Will write code for food.
void Void(void) { Void(); } /* The recursive call of the void */

[Mut...@dastardlyhq.com]

On Sat, 27 May 2023 16:41:36 -0700
Keith Thompson <Keith.S.T...@gmail.com> wrote:
>Michael S <already...@yahoo.com> writes:
>> On Thursday, May 25, 2023 at 9:58:57 PM UTC+3, David Brown wrote:
>>> As a test of how authentic it is, I guess that most people in this group
>>> can understand most of the poem. But if you look up some Chaucer or
>>> other real Middle English poetry, I doubt you'll have much idea at all
>>> about what it is saying - at least not without a lot of effort.
>>
>> That's exactly what caused my suspicions. If non-native like myself
>> can understand it then it can't be too authentic.
>
>The first line struck me as a likely grammatical error:
>
> In the realme of programmynge, C++ doth resideth,
>
>The modern English equivalent would be "... does resides", which should
>be "does reside". I don't know the grammatical rules of Middle English,
>but I would have expected "doth reside".
>
>My own experiments with ChatGPT do not suggest that it "knows" enough to
>generate correct Middle English. (On the other hand, Middle English
>grammar was probably not at all strict, so maybe "doth resideth" would
>be perfectly acceptable.)

Spelling was pretty fluid in the middle ages, varying from region to region
and even between people, but I don't know if the grammar did too (until you
went a long way north).

[David Brown]

On 28/05/2023 01:41, Keith Thompson wrote:
> Michael S <already...@yahoo.com> writes:
>> On Thursday, May 25, 2023 at 9:58:57 PM UTC+3, David Brown wrote:
>>> As a test of how authentic it is, I guess that most people in this group
>>> can understand most of the poem. But if you look up some Chaucer or
>>> other real Middle English poetry, I doubt you'll have much idea at all
>>> about what it is saying - at least not without a lot of effort.
>>
>> That's exactly what caused my suspicions. If non-native like myself
>> can understand it then it can't be too authentic.
>
> The first line struck me as a likely grammatical error:
>
> In the realme of programmynge, C++ doth resideth,
>
> The modern English equivalent would be "... does resides", which should
> be "does reside". I don't know the grammatical rules of Middle English,
> but I would have expected "doth reside".
>

That would be correct, to my knowledge. (It is, however, a /long/ time
since I studies Chaucer.)

> My own experiments with ChatGPT do not suggest that it "knows" enough to
> generate correct Middle English. (On the other hand, Middle English
> grammar was probably not at all strict, so maybe "doth resideth" would
> be perfectly acceptable.)
>

The grammar of languages of that age was quite strict, as far as is
known, but spelling was left more up to the individual - books were
seldom mass-produced, since they had to be copied by hand, and literacy
was rare outside of the church. It is important to remember that
"Middle English" was not a single fixed language - the term spans about
four hundred years and many regions with their own variations. Still,
the basic language structure was the same, and "doth reside" would be
the correct form right up until modern English when "doth" morphed into
"does".

Some leeway for bending or breaking the rules can be accepted in poetry,
but I suspect it is more likely that ChatGPT got it wrong than it
knowingly took liberties to make the lines rhyme.

[Kalevi Kolttonen]

David Brown <david...@hesbynett.no> wrote:
> That would be correct, to my knowledge. (It is, however, a /long/ time
> since I studies Chaucer.)

Nearly 30 years ago, I studied English language in the University.
One of the courses was about Old English and Middle English. We
had to translate those texts into Finnish.

One of the pitfalls in either Old or Middle English (cannot remember
which) is that it contains words that are still in use today. However,
their meaning back in the old days was completely different, so you
have to use a dictionary practically all the time when translating.

br,
KK

[David Brown]

On 29/05/2023 17:47, Kalevi Kolttonen wrote:
> David Brown <david...@hesbynett.no> wrote:
>> That would be correct, to my knowledge. (It is, however, a /long/ time
>> since I studies Chaucer.)
>
> Nearly 30 years ago, I studied English language in the University.
> One of the courses was about Old English and Middle English. We
> had to translate those texts into Finnish.
>

That is impressive! As has been said in this thread, it is possible,
but hard, to understand some Middle English if you are fluent in modern
English. Chaucer is sometimes studied at school in Britain if you are
doing English in your final couple of years. But you can expect to have
to look up a lot of the words.

Old English, on the other hand, is Anglo Saxon - it is significantly
different from Middle English, and even uses a fair number of different
letters when written. So studying that as a Finn is no small feat.

> One of the pitfalls in either Old or Middle English (cannot remember
> which) is that it contains words that are still in use today. However,
> their meaning back in the old days was completely different, so you
> have to use a dictionary practically all the time when translating.
>

There are plenty of modern English words which can be traced back to
Middle and even Old English. And yes, sometimes the meanings can change
significantly over time. That also applies between different modern
languages. Maybe you haven't noticed - Finnish, after all, shares
virtually no vocabulary with other languages except Hungarian, Estonian,
and the Sami languages. So you won't see many of these "false friends"
when learning English. (If you are fluent in Swedish as well, and try
to learn some Norwegian, you'll meet a few "false friends".)

[Kalevi Kolttonen]

David Brown <david...@hesbynett.no> wrote:
> On 29/05/2023 17:47, Kalevi Kolttonen wrote:
>> David Brown <david...@hesbynett.no> wrote:
>>> That would be correct, to my knowledge. (It is, however, a /long/ time
>>> since I studies Chaucer.)
>>
>> Nearly 30 years ago, I studied English language in the University.
>> One of the courses was about Old English and Middle English. We
>> had to translate those texts into Finnish.
>>
>
> That is impressive!

Well, not really. The texts were rather short. One A4 sheet
at most.

I remember that the teacher liked my translations, but all
of it would have been impossible without the dictionary.

br,
KK

[Mut...@dastardlyhq.com]

My favourite false friend phrase is "pet sale". In french it means "dirty
fart". :)

[Vir Campestris]

I studied French at school, and did a few years of Latin. Italian
Spanish and German aren't complete black holes either - I can sometimes
guess what that road sign means... the fact that my wife is a linguist
helps.

But Finnish? You have a different language. It means almost nothing to
me. Coming from that as your native tongue to the level you are in
English to the fluency that you have is really impressive.

The other end of the scale is an ex-colleague of mine who worked in
Germany for several years, and didn't learn the language. My reaction
wasn't "Why?" but "How?". Given all the signs, menus, and everything
else written around you how could you not pick some up?

Andy

[David Brown]

I've known people to live here in Norway for decades without learning
more than a few words. But this is a small country - a lot here is in
English, rather than translated, which is not the case for Germany.

[Mut...@dastardlyhq.com]

I have a friend who's lived in Finland for 15 years and still can't
speak a word of Finnish. Whenever I ask him how its going I get some
mumbling about not got the time. Huh? IMO he's just lazy since because a lot
of people in Finland speak english he doesn't have to bother speaking
finnish.

[David Brown]

It is easier for a Finnish speaker to learn English, than vice versa,
due to the different kinds of language and grammar (English is a very
analytic language - it uses pronouns, helper verbs, and separate words.
Finnish is very synthetic, meaning different tenses or pronouns get
combined within a single long constructed word).

It is also easier to learn another language when you are younger - Finns
learn English from a young age at school, while few non-Finns learn
Finnish at school. And outside school, Finns meet a lot of English in
daily life, such as internet use - non-Finns only see Finnish in
internet memes about how hard it is to learn Finnish.

Still, I think if you live in a different country it is important to try
to learn the language, even if you never really master it.

[Mut...@dastardlyhq.com]

Completely agree. I've spent the last 10 years relearning french after
a 20 year gap from school and I know I'll never be fluent in it but I can
get by in conversation and I'm quite good at reading. If you make the effort
you get the results.