Groups | Search | Server Info | Keyboard shortcuts | Login | Register [http] [https] [nntp] [nntps]


Groups > alt.comp.os.windows-10 > #183363 > unrolled thread

Scary AI

Started byEd Cryer <ed@somewhere.in.the.uk>
First post2025-04-08 16:26 +0100
Last post2025-04-18 01:02 +0300
Articles 8 on this page of 28 — 10 participants

Back to article view | Back to alt.comp.os.windows-10


Contents

  Scary AI Ed Cryer <ed@somewhere.in.the.uk> - 2025-04-08 16:26 +0100
    Re: Scary AI "Alan K." <alan@invalid.com> - 2025-04-08 11:45 -0400
    Re: Scary AI Newyana2 <newyana@invalid.nospam> - 2025-04-08 12:39 -0400
      Re: Scary AI Ed Cryer <ed@somewhere.in.the.uk> - 2025-04-08 19:07 +0100
        Re: Scary AI Newyana2 <newyana@invalid.nospam> - 2025-04-08 14:45 -0400
          Re: Scary AI Ed Cryer <ed@somewhere.in.the.uk> - 2025-04-08 20:35 +0100
            Re: Scary AI jetjock <jetjock@unkown.com> - 2025-04-09 14:01 -0500
          Re: Scary AI Chris <ithinkiam@gmail.com> - 2025-04-08 20:57 +0000
            Re: Scary AI Newyana2 <newyana@invalid.nospam> - 2025-04-08 17:16 -0400
              Re: Scary AI Chris <ithinkiam@gmail.com> - 2025-04-09 19:53 +0000
                Re: Scary AI Newyana2 <newyana@invalid.nospam> - 2025-04-09 16:47 -0400
                  Re: Scary AI Chris <ithinkiam@gmail.com> - 2025-04-11 12:23 +0000
                    Re: Scary AI Newyana2 <newyana@invalid.nospam> - 2025-04-11 13:31 -0400
                      Re: Scary AI Chris <ithinkiam@gmail.com> - 2025-04-13 02:30 +0000
                        Re: Scary AI Newyana2 <newyana@invalid.nospam> - 2025-04-13 07:49 -0400
                          Re: Scary AI Chris <ithinkiam@gmail.com> - 2025-04-13 13:08 +0000
                      Re: Scary AI Chris <ithinkiam@gmail.com> - 2025-04-13 02:38 +0000
              Re: Scary AI Anton Shepelev <anton.txt@gmail.moc> - 2025-04-18 01:40 +0300
                Re: Scary AI Newyana2 <newyana@invalid.nospam> - 2025-04-17 20:22 -0400
                  Re: Scary AI Borax Man <rotflol2@hotmail.com> - 2025-04-18 02:12 +0000
                    Re: Scary AI Chris <ithinkiam@gmail.com> - 2025-04-18 06:44 +0000
                  Re: Scary AI Anton Shepelev <anton.txt@g{oogle}mail.com> - 2025-04-18 14:34 +0300
        Re: Scary AI Chris <ithinkiam@gmail.com> - 2025-04-08 20:46 +0000
          Re: Scary AI Ed Cryer <ed@somewhere.in.the.uk> - 2025-04-08 22:48 +0100
            Re: Scary AI Chris <ithinkiam@gmail.com> - 2025-04-09 09:50 +0000
      Re: Scary AI occam <occam@nowhere.nix> - 2025-04-18 16:45 +0200
    Re: Scary AI Steve Hayes <hayesstw@telkomsa.net> - 2025-04-09 05:29 +0200
    Re: Scary AI Anton Shepelev <anton.txt@gmail.moc> - 2025-04-18 01:02 +0300

Page 2 of 2 — ← Prev page 1 [2]


#183802

FromChris <ithinkiam@gmail.com>
Date2025-04-18 06:44 +0000
Message-ID<vtssca$2fls9$1@dont-email.me>
In reply to#183799
Borax Man <rotflol2@hotmail.com> wrote:
> ["Followup-To:" header set to alt.philosophy.]
> On 2025-04-18, Newyana2 <newyana@invalid.nospam> wrote:
>> On 4/17/2025 6:40 PM, Anton Shepelev wrote:
>>> Newyana2:
>>> 
>>>> If you believe in scientific materialism then you might
>>>> believe that consciousness is an emergent quality, arising
>>>> from chemical reactions in the brain.
>>> 
>>> Is this compatible with us perceiving our own consciousness
>>> and being able to discuss it, which means it is casually
>>> active?
>>> 
>>> Do you mean strong (aka miraculous) emergence, or weak
>>> emergence? IMHO, the weak variety is out of the question:
>>> chemmical, electrical, and other material processes can
>>> produce only other material processes, but not feelings,
>>> emotions, qualia...
>>> 
>> 
>> I don't support either premise. Do we perceive
>> consciousness? That seems questionable. "I think,
>> therefore I am" is a desperate grasping at ground,
>> not an observation.
>> 
> 
> Consciousness being an emergent quality seems like handwaving to me.
> "We don't have the foggiest idea of how it works, so I suppose a
> computer would become conscious because are like computers".

Biology is full of emergent properties that, on the surface, seem to break
physics principles. Life, for example, violates the principle of
conservation of energy. 

A tiger violates newton's third law. You poke it with a stick and it's
response won't be "equal and opposite". 

Emergent properties are a fundamental result of truly complex systems. It
isn't unique to biology. 

> Computation and intelligence are two different things, and our brains,
> our minds work fundamentally different to a Ryzen chip.  Also, if
> conciousness arises from chemical reactions, why not elsewhere?  Why not
> in a beaker?

Depends how complex the beaker is. 

> Consciousness doesn't make sense outside of a living thing, 

Why not? It is possible to explain consciousness without dependency on a
(biological) living thing. It's arguable that a conscious entity then is
also living then gives to ethical discussions around right to life etc.
i.e. if an AI becomes conscious do we have the right to turn it off?

> and it
> likely was selected for during evolution.  This leads to two suggestions
> 
> 1: Consciousness has a real-world difference in how a brain thinks,
> which provides an evolutionary advantage.

Maybe. We would need to be able to disassociate intelligence from
consciousness in terms of their evolutionary advantage. 

> 
> 2: It isn't wholly emergent simply by virtue of a brain being a brain,
> but is something that has to be specifically catered for.  That is to
> say, a computer could only become conscious if we designed it to become
> conscious, which we haven't.

That sounds like an intelligent design argument. 

> 
> I suspect Roger Penrose was onto something when he suggested a link
> between consciousness and Quantum Mechanics, and somewhere during
> evolution nature 'stumbled' on a way of introducing some chaos into
> information processing which made sorting through alternatives much
> faster.
> 


[toc] | [prev] | [next] | [standalone]


#183806

FromAnton Shepelev <anton.txt@g{oogle}mail.com>
Date2025-04-18 14:34 +0300
Message-ID<20250418143417.3cad5e432994109c5e8fa770@g{oogle}mail.com>
In reply to#183795
Followup-To: alt.philosophy

Newyana2:

> Do we perceive consciousness? That seems questionable.
> "I think, therefore I am" is a desperate grasping at ground,
> not an observation.

Not only do I think, but I know and feel that I think.  Were
there no "me", who whould feel and know?  I consider it an
observatino of one's self -- a feat of which only
consciousness is capable.

-- 
()  ascii ribbon campaign -- against html e-mail
/\  www.asciiribbon.org   -- against proprietary attachments

[toc] | [prev] | [next] | [standalone]


#183382

FromChris <ithinkiam@gmail.com>
Date2025-04-08 20:46 +0000
Message-ID<vt41vb$31o43$1@dont-email.me>
In reply to#183370
Ed Cryer <ed@somewhere.in.the.uk> wrote:
> Newyana2 wrote:
>> On 4/8/2025 11:26 AM, Ed Cryer wrote:
>>> 
>>> I thought I'd have a laugh, so I asked ChatGPT for a sonnet in the 
>>> style of Shakespeare. What it gave me has caused me to gulp with 
>>> astonishment. It looks pretty good to me; maybe a little more modern 
>>> English than Elizabethan, but, still, it has a spark; as well as good 
>>> iambic pentameters and rhymes.
>>> 
>>> ******************
>>> 
>>> You said:
>>> write a sonnet in the style of shakespeare
>>> ChatGPT said:
>>> Certainly! Here's a Shakespearean-style sonnet for you:
>>> 
>>> When twilight falls and paints the skies with gold,
>>> The stars emerge, as whispers of the night;
>>> The moon, a silver orb, her secrets told,
>>> And soft winds sing of dreams within our sight.
>>> 
>>> Yet time, that thief, doth steal from youth's bright flame,
>>> And bids us age before the hour is due.
>>> No mortal heart can stay its endless claim,
>>> Though love may bloom and linger, ever true.
>>> 
>>> But in your eyes, I find the world anew,
>>> A spark that lights the path through shadowed days;
>>> A love that beats within my soul, so true,
>>> To guide me through life's ever-winding maze.
>>> 
>>> So let the years pass on, as they must go,
>>> For in your love, I find eternal glow.
>>> 
>>> I hope this resonates with you!
>> 
>>   It sounds like Mr. Hallmark had a few too many drinks.
>> 
>>   I'll be happy when the AI craze blows over, leaving
>> a light of blessed clarity, replacing fake intelligence's
>> winding maze, and let me just say eternal and true
>> love and all that good stuff.
>> 
> 
> How does the program do that?
> I used to earn my daily bread programming commercial mainframes. But 
> this AI "in the style of" beats me. I've done Walt Whitman, Louis 
> Carroll, William Wordsworth and others; and all win my praise.
> And that's only one facet of the AI phenomenon.
> 
> I'd have needed a vast database of examples set up just for Shakespeare 
> alone.
> 
> I'll not rest until I grab the working essentials of how this thing 
> works; call it a program, call it an algorithm, call it what the hell 
> you want, but I want to know how it produces its stuff.
> The sort of things I've read so far are; "It has all the Internet at its 
> call, and summons up vast resources". But that gives nothing away. If 
> you've ever had to write a computer program, you'll know that is true.
> 
> So, how does it do its stuff?

It learns through example in simplistic mimicry of a brain. You don't write
a whole bunch of if statements describing a cat as best you can whilst
avoiding misidentifying a fox. 

Instead, at the basic level, you provide a learning algorithm - which is
usually an existing library of statistical models- a huge catalogue of cat
pictures in different poses and contexts. You describe these pictures via a
complex set of feature descriptors using only the pixel data. When - or if
- you have the right dataset and featureset the algorithm will have
"learnt" the optimal combination to best describe a cat from a photo. This
is stored as a huge matrix of numbers which are uninterpretable by humans,
but then can be used to identify cats in new photos. 

Large language models (LLMs) are much more complex and, as you've found,
have learned some very detailed nuances of human language. i.e. know the
difference between Walt Whitmam and Shakespeare. 

The clever bit is identifying which statistical models work well and
programming the libraries to be as generic possible. 

[toc] | [prev] | [next] | [standalone]


#183392

FromEd Cryer <ed@somewhere.in.the.uk>
Date2025-04-08 22:48 +0100
Message-ID<vt45k5$33s1q$1@dont-email.me>
In reply to#183382
Chris wrote:
> Ed Cryer <ed@somewhere.in.the.uk> wrote:
>> Newyana2 wrote:
>>> On 4/8/2025 11:26 AM, Ed Cryer wrote:
>>>>
>>>> I thought I'd have a laugh, so I asked ChatGPT for a sonnet in the
>>>> style of Shakespeare. What it gave me has caused me to gulp with
>>>> astonishment. It looks pretty good to me; maybe a little more modern
>>>> English than Elizabethan, but, still, it has a spark; as well as good
>>>> iambic pentameters and rhymes.
>>>>
>>>> ******************
>>>>
>>>> You said:
>>>> write a sonnet in the style of shakespeare
>>>> ChatGPT said:
>>>> Certainly! Here's a Shakespearean-style sonnet for you:
>>>>
>>>> When twilight falls and paints the skies with gold,
>>>> The stars emerge, as whispers of the night;
>>>> The moon, a silver orb, her secrets told,
>>>> And soft winds sing of dreams within our sight.
>>>>
>>>> Yet time, that thief, doth steal from youth's bright flame,
>>>> And bids us age before the hour is due.
>>>> No mortal heart can stay its endless claim,
>>>> Though love may bloom and linger, ever true.
>>>>
>>>> But in your eyes, I find the world anew,
>>>> A spark that lights the path through shadowed days;
>>>> A love that beats within my soul, so true,
>>>> To guide me through life's ever-winding maze.
>>>>
>>>> So let the years pass on, as they must go,
>>>> For in your love, I find eternal glow.
>>>>
>>>> I hope this resonates with you!
>>>
>>>    It sounds like Mr. Hallmark had a few too many drinks.
>>>
>>>    I'll be happy when the AI craze blows over, leaving
>>> a light of blessed clarity, replacing fake intelligence's
>>> winding maze, and let me just say eternal and true
>>> love and all that good stuff.
>>>
>>
>> How does the program do that?
>> I used to earn my daily bread programming commercial mainframes. But
>> this AI "in the style of" beats me. I've done Walt Whitman, Louis
>> Carroll, William Wordsworth and others; and all win my praise.
>> And that's only one facet of the AI phenomenon.
>>
>> I'd have needed a vast database of examples set up just for Shakespeare
>> alone.
>>
>> I'll not rest until I grab the working essentials of how this thing
>> works; call it a program, call it an algorithm, call it what the hell
>> you want, but I want to know how it produces its stuff.
>> The sort of things I've read so far are; "It has all the Internet at its
>> call, and summons up vast resources". But that gives nothing away. If
>> you've ever had to write a computer program, you'll know that is true.
>>
>> So, how does it do its stuff?
> 
> It learns through example in simplistic mimicry of a brain. You don't write
> a whole bunch of if statements describing a cat as best you can whilst
> avoiding misidentifying a fox.
> 
> Instead, at the basic level, you provide a learning algorithm - which is
> usually an existing library of statistical models- a huge catalogue of cat
> pictures in different poses and contexts. You describe these pictures via a
> complex set of feature descriptors using only the pixel data. When - or if
> - you have the right dataset and featureset the algorithm will have
> "learnt" the optimal combination to best describe a cat from a photo. This
> is stored as a huge matrix of numbers which are uninterpretable by humans,
> but then can be used to identify cats in new photos.
> 
> Large language models (LLMs) are much more complex and, as you've found,
> have learned some very detailed nuances of human language. i.e. know the
> difference between Walt Whitmam and Shakespeare.
> 
> The clever bit is identifying which statistical models work well and
> programming the libraries to be as generic possible.
> 
> 

Thanks for this.
This sounds much more within the bounds of my understanding of computer 
programming. If I comprehend you a-right, then the modern AI capability 
depends on hundreds and hundreds of previously written and tested routines.
These exist scattered around the Net, and our AI knows where to get them.

The scary part is the novelty of it all; and the novelty is available 
because of two things; 1. the availability of the routines, and 2. the 
speed of modern CPUs.

Ed

[toc] | [prev] | [next] | [standalone]


#183406

FromChris <ithinkiam@gmail.com>
Date2025-04-09 09:50 +0000
Message-ID<vt5fso$cqkl$1@dont-email.me>
In reply to#183392
Ed Cryer <ed@somewhere.in.the.uk> wrote:
> Chris wrote:
>> Ed Cryer <ed@somewhere.in.the.uk> wrote:
>>> Newyana2 wrote:
>>>> On 4/8/2025 11:26 AM, Ed Cryer wrote:
>>>>> 
>>>>> I thought I'd have a laugh, so I asked ChatGPT for a sonnet in the
>>>>> style of Shakespeare. What it gave me has caused me to gulp with
>>>>> astonishment. It looks pretty good to me; maybe a little more modern
>>>>> English than Elizabethan, but, still, it has a spark; as well as good
>>>>> iambic pentameters and rhymes.
>>>>> 
>>>>> ******************
>>>>> 
>>>>> You said:
>>>>> write a sonnet in the style of shakespeare
>>>>> ChatGPT said:
>>>>> Certainly! Here's a Shakespearean-style sonnet for you:
>>>>> 
>>>>> When twilight falls and paints the skies with gold,
>>>>> The stars emerge, as whispers of the night;
>>>>> The moon, a silver orb, her secrets told,
>>>>> And soft winds sing of dreams within our sight.
>>>>> 
>>>>> Yet time, that thief, doth steal from youth's bright flame,
>>>>> And bids us age before the hour is due.
>>>>> No mortal heart can stay its endless claim,
>>>>> Though love may bloom and linger, ever true.
>>>>> 
>>>>> But in your eyes, I find the world anew,
>>>>> A spark that lights the path through shadowed days;
>>>>> A love that beats within my soul, so true,
>>>>> To guide me through life's ever-winding maze.
>>>>> 
>>>>> So let the years pass on, as they must go,
>>>>> For in your love, I find eternal glow.
>>>>> 
>>>>> I hope this resonates with you!
>>>> 
>>>>   It sounds like Mr. Hallmark had a few too many drinks.
>>>> 
>>>>   I'll be happy when the AI craze blows over, leaving
>>>> a light of blessed clarity, replacing fake intelligence's
>>>> winding maze, and let me just say eternal and true
>>>> love and all that good stuff.
>>>> 
>>> 
>>> How does the program do that?
>>> I used to earn my daily bread programming commercial mainframes. But
>>> this AI "in the style of" beats me. I've done Walt Whitman, Louis
>>> Carroll, William Wordsworth and others; and all win my praise.
>>> And that's only one facet of the AI phenomenon.
>>> 
>>> I'd have needed a vast database of examples set up just for Shakespeare
>>> alone.
>>> 
>>> I'll not rest until I grab the working essentials of how this thing
>>> works; call it a program, call it an algorithm, call it what the hell
>>> you want, but I want to know how it produces its stuff.
>>> The sort of things I've read so far are; "It has all the Internet at its
>>> call, and summons up vast resources". But that gives nothing away. If
>>> you've ever had to write a computer program, you'll know that is true.
>>> 
>>> So, how does it do its stuff?
>> 
>> It learns through example in simplistic mimicry of a brain. You don't write
>> a whole bunch of if statements describing a cat as best you can whilst
>> avoiding misidentifying a fox.
>> 
>> Instead, at the basic level, you provide a learning algorithm - which is
>> usually an existing library of statistical models- a huge catalogue of cat
>> pictures in different poses and contexts. You describe these pictures via a
>> complex set of feature descriptors using only the pixel data. When - or if
>> - you have the right dataset and featureset the algorithm will have
>> "learnt" the optimal combination to best describe a cat from a photo. This
>> is stored as a huge matrix of numbers which are uninterpretable by humans,
>> but then can be used to identify cats in new photos.
>> 
>> Large language models (LLMs) are much more complex and, as you've found,
>> have learned some very detailed nuances of human language. i.e. know the
>> difference between Walt Whitmam and Shakespeare.
>> 
>> The clever bit is identifying which statistical models work well and
>> programming the libraries to be as generic possible.
>> 
>> 
> 
> Thanks for this.
> This sounds much more within the bounds of my understanding of computer 
> programming. If I comprehend you a-right, then the modern AI capability 
> depends on hundreds and hundreds of previously written and tested routines.
> These exist scattered around the Net, and our AI knows where to get them.

Not quite. The only thing that's scattered is the data. The AI libraries
are freely available i.e. sci-kit learn written in python
https://scikit-learn.org/stable/index.html

A team of humans manage the learning process to meet the needs of their
goals. 

> 
> The scary part is the novelty of it all; and the novelty is available 
> because of two things; 1. the availability of the routines, and 2. the 
> speed of modern CPUs.

Yes the speed of GPUs (not CPUs) has been revolutionary plus the internet
has made terabytes of data easily (although rarely legally) available. 
However, the algorithms have been around decades. 

[toc] | [prev] | [next] | [standalone]


#183807

Fromoccam <occam@nowhere.nix>
Date2025-04-18 16:45 +0200
Message-ID<m6f6rkFnbslU1@mid.individual.net>
In reply to#183367
On 08/04/2025 18:39, Newyana2 wrote:
> On 4/8/2025 11:26 AM, Ed Cryer wrote:
>>

<ChatGPT Shakespeare sonnet deleted>

Yes, it is a scarily good imitation.
> 

<Newyana2 glib statement deleted>

> 
>   I'll be happy when the AI craze blows over,

It won't. If you don't believe me - hold your breath.

> leaving
> a light of blessed clarity, replacing fake intelligence's
> winding maze, and let me just say eternal and true
> love and all that good stuff.
> 

Did you write that, or did you have Mr. Hallmark do it for you?

[toc] | [prev] | [next] | [standalone]


#183401

FromSteve Hayes <hayesstw@telkomsa.net>
Date2025-04-09 05:29 +0200
Message-ID<skpbvj9udk9faqb5f3hmpjuipe7a15lfjh@4ax.com>
In reply to#183363
On Tue, 8 Apr 2025 16:26:30 +0100, Ed Cryer <ed@somewhere.in.the.uk>
wrote:

>
>I thought I'd have a laugh, so I asked ChatGPT for a sonnet in the style 
>of Shakespeare. What it gave me has caused me to gulp with astonishment. 
>It looks pretty good to me; maybe a little more modern English than 
>Elizabethan, but, still, it has a spark; as well as good iambic 
>pentameters and rhymes.

I used an AI program to generate pictures to use in a book cover
illustration. I gave it descriptions of the main characters, and in
the 8th or 9th attempt it produced pictures more or less as I pictured
them. 

You can see the process and the result here:

<https://methodius.blogspot.com/2025/01/fantasy-adventure-stories-for-kids.html>

But I didn't want to do a human artist out of a job, so I used the
picture as a specification for a human artist: design a book cover
with kids like these. They don't have to be in the smae poses or
wearing the same clothes, but they should like something like the kids
in the picture.

What I've had so far is offers from people who have used AI to
manipulate the sample I posted, usually with horrible results.

 


-- 
Steve Hayes from Tshwane, South Africa
Web:  http://www.khanya.org.za/stevesig.htm
Blog: http://khanya.wordpress.com
E-mail - see web page, or parse: shayes at dunelm full stop org full stop uk

[toc] | [prev] | [next] | [standalone]


#183781

FromAnton Shepelev <anton.txt@gmail.moc>
Date2025-04-18 01:02 +0300
Message-ID<20250418010235.b6cd35d18e7c2199b928d242@gmail.moc>
In reply to#183363
Ed Cryer:

> I thought I'd have a laugh, so I asked ChatGPT for a
> sonnet in the style of Shakespeare. What it gave me has
> caused me to gulp with astonishment.  It looks pretty good
> to me; maybe a little more modern English than
> Elizabethan, but, still, it has a spark; as well as good
> iambic pentameters and rhymes.

Yes, it should give AI pooh-poohers some serious concerns.

> When twilight falls and paints the skies with gold,

Now this is unadultered trash.  It is the Sun, or sunset, that
paints the sky gold (not with gold).

> The stars emerge, as whispers of the night;

No, the stars emerge later, after sundown.  At this level,
AI-generated sonnets are trash, but it is making fearful
progress, and the sooner it stop the higher our chances
of survival as human beings.

IMHO, the rational attude towards AI is fear:

  1.  One should know it is the dehumaniser --  a fact its
      proponents try to hide behind the euphemism
      `transhumanism'.

  2.  AI is the disuniter of people, making inter-human
      communication less necessary then ever in history.
      Google is your friend? Phew -- the LLM is your new
      friend.

  3.  AI is the joy-killer.  It discourages human
      creativity, by replacing humans in creative jobs, and
      by making it deceptfully easy to sort of "create" art
      by promting the AI to do so and calling the result
      yours (which it is not):
      // <https://chronicles.mad-scientist.club/tales/on-ethical-ai/>

  4.  Last but not least, we humans desperately need
      friction, whereas AI is the ultimate lube.
      // <https://blog.darylsun.page/2025/01/23/se-5-indieweb-carnival-january-2025>

The least one can do about it, is assiduosly to ignore
everything related to AI, as if did not exist, and continue
producing genuine human work and art.

Then, one should avoid (dis-)services like Github and Gitlab
that let AI crawlers to launder your work, be it images,
text, or code.  Avoid AI-firendly services and prefer AI-
phobic, or AI-hostile ones.  catbox.moe, for example,
promises never to cooperate with AI companies:
// <https://catbox.moe/faq.php>
If you have a website, consider joining the no-AI webring,
// <https://baccyflap.com/noai/>
filtering out prose launderers with robots.txt and ai.txt,
enforcing robots.txt
// <https://github.com/ai-robots-txt/ai.robots.txt>
and poisoning the AI crawlers like the filthy rats they are:
// https://iocaine.madhouse-project.org/

-- 
()  ascii ribbon campaign -- against html e-mail
/\  www.asciiribbon.org   -- against proprietary attachments

[toc] | [prev] | [standalone]


Page 2 of 2 — ← Prev page 1 [2]

Back to top | Article view | alt.comp.os.windows-10


csiph-web