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

Groups > sci.logic > #345657 > unrolled thread

Paul Tarau versus Mr. Taskmanager, who would win? [A PDP-11 Humunkulus from 1979]

Back to article view | Back to sci.logic

Contents

  Paul Tarau versus Mr. Taskmanager, who would win? [A PDP-11 Humunkulus from 1979] Mild Shock <janburse@fastmail.fm> - 2026-04-24 02:46 +0200
    AI dooms day escape: Güttinger Wald (Re: Paul Tarau versus Mr. Taskmanager, who would win?) Mild Shock <janburse@fastmail.fm> - 2026-04-25 14:06 +0200
      Elmos Fascist Dreams of a 365 Prolog (Was: AI dooms day escape: Güttinger Wald) Mild Shock <janburse@fastmail.fm> - 2026-05-09 12:52 +0200
        Even the Buddos are clueless [Did Tarau see Liliputians?] (Re: Elmos Fascist Dreams of a 365 Prolog) Mild Shock <janburse@fastmail.fm> - 2026-05-09 15:19 +0200
          Halfing the AI Laptop Budget: Ne-Meow sold out! (Re: Even the Buddos are clueless [Did Tarau see Liliputians?]) Mild Shock <janburse@fastmail.fm> - 2026-05-10 09:09 +0200
      Prolog Expert Ginis (PEGs) on a Keychain (Re: AI dooms day escape: Güttinger Wald) Mild Shock <janburse@fastmail.fm> - 2026-06-20 13:04 +0800
        Chatbot Classified as a Weapon (Re: Prolog Expert Ginis (PEGs) on a Keychain) Mild Shock <janburse@fastmail.fm> - 2026-06-21 05:39 +0800
      AI Laptops are just strange novel xBoxes (Was: AI dooms day escape: Güttinger Wald) Mild Shock <janburse@fastmail.fm> - 2026-07-08 20:44 +0200
        Re: AI Laptops are just strange novel xBoxes (Was: AI dooms day escape: Güttinger Wald) "Chris M. Thomasson" <chris.m.thomasson.1@gmail.com> - 2026-07-08 15:22 -0700
          TDR solutions --> work slicing (Was: AI Laptops are just strange novel xBoxes) Mild Shock <janburse@fastmail.fm> - 2026-07-09 09:47 +0200
            Thinking of Chris M. Thomasson: From shadertoys to computetoys? (Re: TDR solutions --> work slicing) Mild Shock <janburse@fastmail.fm> - 2026-07-09 09:52 +0200
      FYI: Unified Memory Architecture (UMA) (Re: Implementing Gas for a Compute Shader [Avoid TDR]) Mild Shock <janburse@fastmail.fm> - 2026-07-09 19:43 +0200
        The Wider von Neumann Neck (Re: FYI: Unified Memory Architecture (UMA)) Mild Shock <janburse@fastmail.fm> - 2026-07-10 07:51 +0200
          The new MIMD Warp is the cherry on top (Re: The Wider von Neumann Neck) Mild Shock <janburse@fastmail.fm> - 2026-07-10 08:08 +0200
          Dumbwit, just run it on your RTX 5070 trash (Re: The Wider von Neumann Neck) Mild Shock <janburse@fastmail.fm> - 2026-07-10 15:49 +0200
            We are still waiting for results! [Confused Dumbwit] (Re: We are waiting Dumbwit: 1 Month, 3 Months, .. [node.js dawn]) Mild Shock <janburse@fastmail.fm> - 2026-07-10 22:45 +0200
              404 Brain not Found [GPU saturation] (Re: We are still waiting for results! [Confused Dumbwit]) Mild Shock <janburse@fastmail.fm> - 2026-07-10 23:40 +0200
                I nowhere talked about 10GB/s (Re: 404 Brain not Found [GPU saturation]) Mild Shock <janburse@fastmail.fm> - 2026-07-10 23:41 +0200
                  I nowhere said something about AI (Re: I nowhere talked about 10GB/s) Mild Shock <janburse@fastmail.fm> - 2026-07-10 23:52 +0200
                    What do you not understand in "budget"? (Re: I nowhere said something about AI) Mild Shock <janburse@fastmail.fm> - 2026-07-11 00:08 +0200
                      SWI makes only MLips not GLips (Re: What do you not understand in "budget"?) Mild Shock <janburse@fastmail.fm> - 2026-07-11 00:09 +0200
                        micro penis got hurt by "budget" (Re: SWI makes only MLips not GLips) Mild Shock <janburse@fastmail.fm> - 2026-07-12 19:20 +0200
    Micro Penis Nemesis: Shoe String Budget π-WAM (Was: Paul Tarau versus Mr. Taskmanager, who would win?) Mild Shock <janburse@fastmail.fm> - 2026-07-12 19:26 +0200
      micro penis struggels with mobile grade GPU concept [Redmi Note 14 Pro+ Results] (Re: Micro Penis Nemesis: Shoe String Budget π-WAM) Mild Shock <janburse@fastmail.fm> - 2026-07-12 21:32 +0200
        Micro Penis Existential Crisis: DeepSeek on a Mobile GPU (Re: micro penis struggels with mobile grade GPU concept [Redmi Note 14 Pro+ Results]) Mild Shock <janburse@fastmail.fm> - 2026-07-12 21:47 +0200
          Micro Penis is worse than Sleepy Joe (Re: Micro Penis Existential Crisis: DeepSeek on a Mobile GPU) Mild Shock <janburse@fastmail.fm> - 2026-07-12 23:00 +0200
            Maybe change your pampers? (Was: Micro Penis is worse than Sleepy Joe) Mild Shock <janburse@fastmail.fm> - 2026-07-12 23:01 +0200
              herpes blister rossy boy is confused (Re: Maybe change your pampers?) Mild Shock <janburse@fastmail.fm> - 2026-07-13 06:54 +0200
                nothing gets blocked except your brain [LPDDR5X-RAM] (Re: herpes blister rossy boy is confused) Mild Shock <janburse@fastmail.fm> - 2026-07-13 13:21 +0200
                  flogging a dead horse PCI VRAM graphic cards (Re: nothing gets blocked except your brain [LPDDR5X-RAM]) Mild Shock <janburse@fastmail.fm> - 2026-07-13 13:52 +0200

Page 2 of 2 — ← Prev page 1 [2]

#347801 — SWI makes only MLips not GLips (Re: What do you not understand in "budget"?)

Hi,

 >> can do on old 8088 PC etc.

You are obviously clueless. You don't need
to look at old PCs, they only did KLips.

Nowadays SWI does MLips. So GLips is a leap!

Bye

Mild Shock schrieb:
> Hi,
> 
> 11.4 Giga Lips with a Budget Laptop
> https://github.com/Jean-Luc-Picard-2021/gigabudget
> 
> Budget Laptop means ~1000 USD.
> Thats not big money. The Mac Neo is
> even better only ~500 USD.
> 
> Its still cheaper than a RTX 5070,
> which is around ~4000 USD. So if you
> have some benchmark data for RTX 5070,
> 
> the LIPS, you still pay 4x times more
> for each LIPS.
> 
> Questions ultra moron?
> 
> Bye
> 
> Junior Romagna schrieb:
>  > Mild Shock wrote:
>  >
>  >> Hi Dumbwit,
>  >>
>  >> Nobody is interested in discussing AI,
>  >> I am discussing prolog on a AI laptop.
>  >>
>  >> Who cares that they use the AI marketing,
>  >> when they have splendid GPUs?
>  >
>  > what an idiot, so you put big money in AI laptop do do graphics you 
> can do
>  > on old 8088 PC etc. Thanks, you just proved you are so fucking stoopid
>  >
>  > i can see now why morons like you are using crappy scripting languages
>  > like prolog. No brain required, the prolog is doing the brain for you
>  >

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

#347833 — micro penis got hurt by "budget" (Re: SWI makes only MLips not GLips)

Hi,

Well I wrote:

 > At the end of 2025 we acquired a couple of AI
 > Laptops , that were still cheap, since RAM prices
 > had not yet rocketed.
 > https://github.com/Jean-Luc-Picard-2021/gigabudget

Here is what I payed, in 2025:

Brack.ch    Swift Go 16 AI               1’359.00 CHF
inter Discount    Lenovo Yoga 7                1’199.95 CHF
Lenovo Schweiz    ThinkCentre Qualcomm           626.58 CHF

Now take the average price, its ca. 1000 CHF
The Swift Go 16 AI is the Ryzen AI 7 350 w/
Radeon 860M. Its an ultra thin laptop, and

the used Radeon 860M is a mobile grade GPU.
Whats your prololoproblem micro penis?

Bye

Loman Barabashev schrieb:
 > Mild Shock wrote:
 >
 >> Hi,
 >>
 >> 11.4 Giga Lips with a Budget Laptop
 >> https://github.com/Jean-Luc-Picard-2021/gigabudget
 >>
 >> Budget Laptop means ~1000 USD.
 >> Thats not big money. The Mac Neo is even better only ~500 USD.
 >
 > you stinking sack of rocks, you can't read your
 > own redundant links. Watch the prices for the Ryzen
 > AI laptops. Fucking idiot. Not worth the price
 > for what they give in AI. Those are embedded cpu/gpu
 > cretin, you don't need to read more.

Mild Shock schrieb:
> Hi,
> 
>  >> can do on old 8088 PC etc.
> 
> You are obviously clueless. You don't need
> to look at old PCs, they only did KLips.
> 
> Nowadays SWI does MLips. So GLips is a leap!
> 
> Bye
> 
> Mild Shock schrieb:
>> Hi,
>>
>> 11.4 Giga Lips with a Budget Laptop
>> https://github.com/Jean-Luc-Picard-2021/gigabudget
>>
>> Budget Laptop means ~1000 USD.
>> Thats not big money. The Mac Neo is
>> even better only ~500 USD.
>>
>> Its still cheaper than a RTX 5070,
>> which is around ~4000 USD. So if you
>> have some benchmark data for RTX 5070,
>>
>> the LIPS, you still pay 4x times more
>> for each LIPS.
>>
>> Questions ultra moron?
>>
>> Bye
>>
>> Junior Romagna schrieb:
>>  > Mild Shock wrote:
>>  >
>>  >> Hi Dumbwit,
>>  >>
>>  >> Nobody is interested in discussing AI,
>>  >> I am discussing prolog on a AI laptop.
>>  >>
>>  >> Who cares that they use the AI marketing,
>>  >> when they have splendid GPUs?
>>  >
>>  > what an idiot, so you put big money in AI laptop do do graphics you 
>> can do
>>  > on old 8088 PC etc. Thanks, you just proved you are so fucking stoopid
>>  >
>>  > i can see now why morons like you are using crappy scripting languages
>>  > like prolog. No brain required, the prolog is doing the brain for you
>>  >
> 

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

#347834 — Micro Penis Nemesis: Shoe String Budget π-WAM (Was: Paul Tarau versus Mr. Taskmanager, who would win?)

Hi,

Micro Penis the putin payed troll, is now
on the payment list of overpriced NVIDIA as
well. He cannot get over the concept of a

Shoe String Budget:

"According to Darren Aronofsky’s debut
1998 film Pi, “everything around us can
be represented and understood through numbers”,
from the stock market to the “wax and wane
of caribou populations”. But, ironically,
the film’s own numerical facts feel particularly
inexplicable. It was made on a budget of just
$60,000, which is less a shoestring and more
just the aglet at the end of a frayed lace.
To put that in to perspective, 1999’s The
Matrix – similarly based around the dystopian
danger of AI – may have been slightly slicker
and sexier, but also was made for $60m, a
thousand times more buck for a thousand
times less bang. Plus, it means that its
profit margin was huge. As Variety’s headline
following its release put it, ‘”π=$1,000,000!”
https://www.vice.com/en/article/pi-soundtrack-20-years-aronofsky-aphex-twin-autechre/

04 Bucephalus Bouncing Ball
https://www.youtube.com/watch?v=Ez6xDGTFswQ

Bye

Loman Barabashev schrieb:
 > I have a micro penis and my brain explodes

Mild Shock schrieb:
> Hi,
> 
> Ok I was looking at this learning challenge,
> producing vector (y1,y2,y3,y4) from a vector
> (x1,x2,x3,x4), System R can do it via least square?
> 
> | 0 0 0 1 |   | x1 |     | x4 |
> | 0 0 1 0 |   | x2 |  =  | x3 |
> | 0 1 0 0 |   | x3 |     | x2 |
> | 1 0 0 0 |   | x4 |     | x1 |
> 
> How it started:
> 
> "multiplicative RNNs arises naturally from a
> proof-theoretic interpretation of next-token
> prediction as nested intuitionistic implication"
> Paul Tarau - 2026
> https://arxiv.org/abs/2601.19915
> 
> How its going:
> 
> "Dave uses a PDP-11 to train a real Neural
> Network complete with Transformers and
> Attention so you can see them at their most basic."
> Mr. Taskmanager - 2026
> https://www.youtube.com/watch?v=OUE3FSIk46g
> 
> We see Doctor Frankstein in action from
> the Bronze Age of Computing, producing
> a Humunkulus, the progenitor of todays
> 
> Bulgakov Shuriks in the Hyperscale Age!
> 
> Bye
> 
> P.S.: My impression neither cut to the core, that
> this incredible transformer most likely
> produced this deterministic attention:
> 
> | -1 | * | k | + | 5 | = | k' |
> 
> Or differently expressed y_k = x_{5-k}.
> 
> How did the transformer do it? It produced
> a neural network with 1216 parameters, but
> didn't use embeddings or polar encoding
> 
> of positions. But if we strip the noise
> and denoise from the position encoding,
> the denoise is done via softmax. We somehow
> 
> must get the above, right? I still need to
> verify my claim! BTW: The PDP-11 assembly
> from 1979 uses wider example not with n=4
> 
> but with n=8.

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

#347844 — micro penis struggels with mobile grade GPU concept [Redmi Note 14 Pro+ Results] (Re: Micro Penis Nemesis: Shoe String Budget π-WAM)

Hi,

It seems micro penis struggles with mobile
grade GPU concept. Whats the difference
between a mobile grade GPU and non-mobile grade

GPU? You know the **M** in **Readeon 860M**
means Mobile! Here is a comparison:

**Mobile GPU:**

Energy Consuption: Low
Device Memory: AUP (accelerator unit processor,
    shares memory with CPU, no VRAM)
Cooling System: Fewer or no fans

**Non-Mobile GPU:**

Energy Consuption: High
Device Memory: DUP (discret unit processor,
    has its own VRAM)
Cooling System: A lot of fans or other cooling

Bye

BTW: Here are some results for:

11.4 Giga Lips with a Budget Laptop
https://github.com/Jean-Luc-Picard-2021/gigabudget

On a smartphone, namely Redmi Note 14 Pro+:

1 Shader
1983 ms

4096 Shaders
16253 ms

The phone uses a Snapdragon 7s Gen 3

Mild Shock schrieb:
> Hi,
> 
> Micro Penis the putin payed troll, is now
> on the payment list of overpriced NVIDIA as
> well. He cannot get over the concept of a
> 
> Shoe String Budget:
> 
> "According to Darren Aronofsky’s debut
> 1998 film Pi, “everything around us can
> be represented and understood through numbers”,
> from the stock market to the “wax and wane
> of caribou populations”. But, ironically,
> the film’s own numerical facts feel particularly
> inexplicable. It was made on a budget of just
> $60,000, which is less a shoestring and more
> just the aglet at the end of a frayed lace.
> To put that in to perspective, 1999’s The
> Matrix – similarly based around the dystopian
> danger of AI – may have been slightly slicker
> and sexier, but also was made for $60m, a
> thousand times more buck for a thousand
> times less bang. Plus, it means that its
> profit margin was huge. As Variety’s headline
> following its release put it, ‘”π=$1,000,000!”
> https://www.vice.com/en/article/pi-soundtrack-20-years-aronofsky-aphex-twin-autechre/ 
> 
> 
> 04 Bucephalus Bouncing Ball
> https://www.youtube.com/watch?v=Ez6xDGTFswQ
> 
> Bye
> 
> Loman Barabashev schrieb:
>  > I have a micro penis and my brain explodes
> 
> Mild Shock schrieb:
>> Hi,
>>
>> Ok I was looking at this learning challenge,
>> producing vector (y1,y2,y3,y4) from a vector
>> (x1,x2,x3,x4), System R can do it via least square?
>>
>> | 0 0 0 1 |   | x1 |     | x4 |
>> | 0 0 1 0 |   | x2 |  =  | x3 |
>> | 0 1 0 0 |   | x3 |     | x2 |
>> | 1 0 0 0 |   | x4 |     | x1 |
>>
>> How it started:
>>
>> "multiplicative RNNs arises naturally from a
>> proof-theoretic interpretation of next-token
>> prediction as nested intuitionistic implication"
>> Paul Tarau - 2026
>> https://arxiv.org/abs/2601.19915
>>
>> How its going:
>>
>> "Dave uses a PDP-11 to train a real Neural
>> Network complete with Transformers and
>> Attention so you can see them at their most basic."
>> Mr. Taskmanager - 2026
>> https://www.youtube.com/watch?v=OUE3FSIk46g
>>
>> We see Doctor Frankstein in action from
>> the Bronze Age of Computing, producing
>> a Humunkulus, the progenitor of todays
>>
>> Bulgakov Shuriks in the Hyperscale Age!
>>
>> Bye
>>
>> P.S.: My impression neither cut to the core, that
>> this incredible transformer most likely
>> produced this deterministic attention:
>>
>> | -1 | * | k | + | 5 | = | k' |
>>
>> Or differently expressed y_k = x_{5-k}.
>>
>> How did the transformer do it? It produced
>> a neural network with 1216 parameters, but
>> didn't use embeddings or polar encoding
>>
>> of positions. But if we strip the noise
>> and denoise from the position encoding,
>> the denoise is done via softmax. We somehow
>>
>> must get the above, right? I still need to
>> verify my claim! BTW: The PDP-11 assembly
>> from 1979 uses wider example not with n=4
>>
>> but with n=8.
> 

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

#347846 — Micro Penis Existential Crisis: DeepSeek on a Mobile GPU (Re: micro penis struggels with mobile grade GPU concept [Redmi Note 14 Pro+ Results])

Hi,

It seems micro penis has a real existential
crisis right now. An alice in wonderland moment,
falling down a rabit whole. Well no wonder

micro penis lives under a rock and has never
heard of the small model revolution that goes
hand in hand with the AI laptop revolution.

Here is a test, running deepseek locally on
a budget laptop (via LM Studio, oMLX, etc..):

qwen3.5-9b-deepseek-v4-flash

Q: Well there is a formidable horse race going on.
Given the danger that I compare apples with oranges.
It is still interesting too see how the Al laptop
landscape is forming.

Thought for 1 minutes 20 seconds

A: You hit on a really crucial point in the Al economy:
the tension between cloud consumption and edge ownership.
When you compare a $0.50 per 1k-token API call with a
$2,000 laptop that runs Qwen3.5 locally for free
(electricity aside), it's not strictly apples-to-oranges
because one is a service and the other is an asset. But
the implications for how we use Al are massive.

Bye

Mild Shock schrieb:
> Hi,
> 
> It seems micro penis struggles with mobile
> grade GPU concept. Whats the difference
> between a mobile grade GPU and non-mobile grade
> 
> GPU? You know the **M** in **Readeon 860M**
> means Mobile! Here is a comparison:
> 
> **Mobile GPU:**
> 
> Energy Consuption: Low
> Device Memory: AUP (accelerator unit processor,
>     shares memory with CPU, no VRAM)
> Cooling System: Fewer or no fans
> 
> **Non-Mobile GPU:**
> 
> Energy Consuption: High
> Device Memory: DUP (discret unit processor,
>     has its own VRAM)
> Cooling System: A lot of fans or other cooling
> 
> Bye
> 
> BTW: Here are some results for:
> 
> 11.4 Giga Lips with a Budget Laptop
> https://github.com/Jean-Luc-Picard-2021/gigabudget
> 
> On a smartphone, namely Redmi Note 14 Pro+:
> 
> 1 Shader
> 1983 ms
> 
> 4096 Shaders
> 16253 ms
> 
> The phone uses a Snapdragon 7s Gen 3
> 
> Mild Shock schrieb:
>> Hi,
>>
>> Micro Penis the putin payed troll, is now
>> on the payment list of overpriced NVIDIA as
>> well. He cannot get over the concept of a
>>
>> Shoe String Budget:
>>
>> "According to Darren Aronofsky’s debut
>> 1998 film Pi, “everything around us can
>> be represented and understood through numbers”,
>> from the stock market to the “wax and wane
>> of caribou populations”. But, ironically,
>> the film’s own numerical facts feel particularly
>> inexplicable. It was made on a budget of just
>> $60,000, which is less a shoestring and more
>> just the aglet at the end of a frayed lace.
>> To put that in to perspective, 1999’s The
>> Matrix – similarly based around the dystopian
>> danger of AI – may have been slightly slicker
>> and sexier, but also was made for $60m, a
>> thousand times more buck for a thousand
>> times less bang. Plus, it means that its
>> profit margin was huge. As Variety’s headline
>> following its release put it, ‘”π=$1,000,000!”
>> https://www.vice.com/en/article/pi-soundtrack-20-years-aronofsky-aphex-twin-autechre/ 
>>
>>
>> 04 Bucephalus Bouncing Ball
>> https://www.youtube.com/watch?v=Ez6xDGTFswQ
>>
>> Bye
>>
>> Loman Barabashev schrieb:
>>  > I have a micro penis and my brain explodes

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

#347860 — Micro Penis is worse than Sleepy Joe (Re: Micro Penis Existential Crisis: DeepSeek on a Mobile GPU)

Hi,

Micro Penis is worse than Sleepy Joe. He
probably only believes the existence of a
hammer, when you hit him on the head with

a hammer. Currently Micro Penis is sitting
there and shitting his pants it seems.

Bye

 > stop polluting this group with nonsense,
 > you stupid unemployed former it-supporter.
 > I shit in your shaders. You were talking
 > about AI. Those ryzen AI laptops are for fools.

Mild Shock schrieb:
> Hi,
> 
> It seems micro penis has a real existential
> crisis right now. An alice in wonderland moment,
> falling down a rabit whole. Well no wonder
> 
> micro penis lives under a rock and has never
> heard of the small model revolution that goes
> hand in hand with the AI laptop revolution.
> 
> Here is a test, running deepseek locally on
> a budget laptop (via LM Studio, oMLX, etc..):
> 
> qwen3.5-9b-deepseek-v4-flash
> 
> Q: Well there is a formidable horse race going on.
> Given the danger that I compare apples with oranges.
> It is still interesting too see how the Al laptop
> landscape is forming.
> 
> Thought for 1 minutes 20 seconds
> 
> A: You hit on a really crucial point in the Al economy:
> the tension between cloud consumption and edge ownership.
> When you compare a $0.50 per 1k-token API call with a
> $2,000 laptop that runs Qwen3.5 locally for free
> (electricity aside), it's not strictly apples-to-oranges
> because one is a service and the other is an asset. But
> the implications for how we use Al are massive.
> 
> Bye
> 
> Mild Shock schrieb:
>> Hi,
>>
>> It seems micro penis struggles with mobile
>> grade GPU concept. Whats the difference
>> between a mobile grade GPU and non-mobile grade
>>
>> GPU? You know the **M** in **Readeon 860M**
>> means Mobile! Here is a comparison:
>>
>> **Mobile GPU:**
>>
>> Energy Consuption: Low
>> Device Memory: AUP (accelerator unit processor,
>>     shares memory with CPU, no VRAM)
>> Cooling System: Fewer or no fans
>>
>> **Non-Mobile GPU:**
>>
>> Energy Consuption: High
>> Device Memory: DUP (discret unit processor,
>>     has its own VRAM)
>> Cooling System: A lot of fans or other cooling
>>
>> Bye
>>
>> BTW: Here are some results for:
>>
>> 11.4 Giga Lips with a Budget Laptop
>> https://github.com/Jean-Luc-Picard-2021/gigabudget
>>
>> On a smartphone, namely Redmi Note 14 Pro+:
>>
>> 1 Shader
>> 1983 ms
>>
>> 4096 Shaders
>> 16253 ms
>>
>> The phone uses a Snapdragon 7s Gen 3
>>
>> Mild Shock schrieb:
>>> Hi,
>>>
>>> Micro Penis the putin payed troll, is now
>>> on the payment list of overpriced NVIDIA as
>>> well. He cannot get over the concept of a
>>>
>>> Shoe String Budget:
>>>
>>> "According to Darren Aronofsky’s debut
>>> 1998 film Pi, “everything around us can
>>> be represented and understood through numbers”,
>>> from the stock market to the “wax and wane
>>> of caribou populations”. But, ironically,
>>> the film’s own numerical facts feel particularly
>>> inexplicable. It was made on a budget of just
>>> $60,000, which is less a shoestring and more
>>> just the aglet at the end of a frayed lace.
>>> To put that in to perspective, 1999’s The
>>> Matrix – similarly based around the dystopian
>>> danger of AI – may have been slightly slicker
>>> and sexier, but also was made for $60m, a
>>> thousand times more buck for a thousand
>>> times less bang. Plus, it means that its
>>> profit margin was huge. As Variety’s headline
>>> following its release put it, ‘”π=$1,000,000!”
>>> https://www.vice.com/en/article/pi-soundtrack-20-years-aronofsky-aphex-twin-autechre/ 
>>>
>>>
>>> 04 Bucephalus Bouncing Ball
>>> https://www.youtube.com/watch?v=Ez6xDGTFswQ
>>>
>>> Bye
>>>
>>> Loman Barabashev schrieb:
>>>  > I have a micro penis and my brain explodes

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

#347861 — Maybe change your pampers? (Was: Micro Penis is worse than Sleepy Joe)

Hi,

Hey micro penis, your shitting start
smelling. Maybe change your pampers?

Bye

Mild Shock schrieb:
> Hi,
> 
> Micro Penis is worse than Sleepy Joe. He
> probably only believes the existence of a
> hammer, when you hit him on the head with
> 
> a hammer. Currently Micro Penis is sitting
> there and shitting his pants it seems.
> 
> Bye
> 
>  > stop polluting this group with nonsense,
>  > you stupid unemployed former it-supporter.
>  > I shit in your shaders. You were talking
>  > about AI. Those ryzen AI laptops are for fools.
> 
> Mild Shock schrieb:
>> Hi,
>>
>> It seems micro penis has a real existential
>> crisis right now. An alice in wonderland moment,
>> falling down a rabit whole. Well no wonder
>>
>> micro penis lives under a rock and has never
>> heard of the small model revolution that goes
>> hand in hand with the AI laptop revolution.
>>
>> Here is a test, running deepseek locally on
>> a budget laptop (via LM Studio, oMLX, etc..):
>>
>> qwen3.5-9b-deepseek-v4-flash
>>
>> Q: Well there is a formidable horse race going on.
>> Given the danger that I compare apples with oranges.
>> It is still interesting too see how the Al laptop
>> landscape is forming.
>>
>> Thought for 1 minutes 20 seconds
>>
>> A: You hit on a really crucial point in the Al economy:
>> the tension between cloud consumption and edge ownership.
>> When you compare a $0.50 per 1k-token API call with a
>> $2,000 laptop that runs Qwen3.5 locally for free
>> (electricity aside), it's not strictly apples-to-oranges
>> because one is a service and the other is an asset. But
>> the implications for how we use Al are massive.
>>
>> Bye
>>
>> Mild Shock schrieb:
>>> Hi,
>>>
>>> It seems micro penis struggles with mobile
>>> grade GPU concept. Whats the difference
>>> between a mobile grade GPU and non-mobile grade
>>>
>>> GPU? You know the **M** in **Readeon 860M**
>>> means Mobile! Here is a comparison:
>>>
>>> **Mobile GPU:**
>>>
>>> Energy Consuption: Low
>>> Device Memory: AUP (accelerator unit processor,
>>>     shares memory with CPU, no VRAM)
>>> Cooling System: Fewer or no fans
>>>
>>> **Non-Mobile GPU:**
>>>
>>> Energy Consuption: High
>>> Device Memory: DUP (discret unit processor,
>>>     has its own VRAM)
>>> Cooling System: A lot of fans or other cooling
>>>
>>> Bye
>>>
>>> BTW: Here are some results for:
>>>
>>> 11.4 Giga Lips with a Budget Laptop
>>> https://github.com/Jean-Luc-Picard-2021/gigabudget
>>>
>>> On a smartphone, namely Redmi Note 14 Pro+:
>>>
>>> 1 Shader
>>> 1983 ms
>>>
>>> 4096 Shaders
>>> 16253 ms
>>>
>>> The phone uses a Snapdragon 7s Gen 3
>>>
>>> Mild Shock schrieb:
>>>> Hi,
>>>>
>>>> Micro Penis the putin payed troll, is now
>>>> on the payment list of overpriced NVIDIA as
>>>> well. He cannot get over the concept of a
>>>>
>>>> Shoe String Budget:
>>>>
>>>> "According to Darren Aronofsky’s debut
>>>> 1998 film Pi, “everything around us can
>>>> be represented and understood through numbers”,
>>>> from the stock market to the “wax and wane
>>>> of caribou populations”. But, ironically,
>>>> the film’s own numerical facts feel particularly
>>>> inexplicable. It was made on a budget of just
>>>> $60,000, which is less a shoestring and more
>>>> just the aglet at the end of a frayed lace.
>>>> To put that in to perspective, 1999’s The
>>>> Matrix – similarly based around the dystopian
>>>> danger of AI – may have been slightly slicker
>>>> and sexier, but also was made for $60m, a
>>>> thousand times more buck for a thousand
>>>> times less bang. Plus, it means that its
>>>> profit margin was huge. As Variety’s headline
>>>> following its release put it, ‘”π=$1,000,000!”
>>>> https://www.vice.com/en/article/pi-soundtrack-20-years-aronofsky-aphex-twin-autechre/ 
>>>>
>>>>
>>>> 04 Bucephalus Bouncing Ball
>>>> https://www.youtube.com/watch?v=Ez6xDGTFswQ
>>>>
>>>> Bye
>>>>
>>>> Loman Barabashev schrieb:
>>>>  > I have a micro penis and my brain explodes
> 

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

#347884 — herpes blister rossy boy is confused (Re: Maybe change your pampers?)

Hi,

herpes blister rossy boy is confused.
One more idiot on the loose that
cannot do research of AI laptop prices.

Here you idiots:

Acer Aspire 14 AI
https://www.digitec.ch/de/s1/product/acer-aspire-14-ai-14-1000-gb-32-gb-ch-amd-ryzen-ai-7-350-notebook-65210813

Price: 999.–
Prozessortyp AMD Ryzen AI 7 350
Grafikkarten Modell Radeon 860M
Onboard Arbeitsspeicher 32 GB
Arbeitsspeichertyp LPDDR5X-RAM

So its even not the case that RAM prices
have affected AI laptop prices that much.

Bye

BTW: The acer company is a taiwan company.
The above laptop from the aspire series,
is a little thicker than the one from the

swift series:

Acer Aspire One – Acer's mid to high-end personal-use laptop
Acer Swift – A series of mid to high-end ultra-portable notebooks

https://en.wikipedia.org/wiki/Acer_Inc.

Ross Finlayson schrieb:
 > On 07/11/2026 05:25 AM, Loman Barabashev wrote:
 >> Mild Shock wrote:
 >>
 >>> Hi,
 >>>
 >>> 11.4 Giga Lips with a Budget Laptop
 >>> https://github.com/Jean-Luc-Picard-2021/gigabudget
 >>>
 >>> Budget Laptop means ~1000 USD.
 >>> Thats not big money. The Mac Neo is even better only ~500 USD.
 >>
 >> you stinking sack of rocks, you can't read your own redundant links. 
Watch
 >> the prices for the Ryzen AI laptops. Fucking idiot. Not worth the price
 >> for what they give in AI. Those are embedded cpu/gpu cretin, you don't
 >> need to read more.
 >>
 >
 > Shut Up, "Burse".

Mild Shock schrieb:
> Hi,
> 
> Hey micro penis, your shitting start
> smelling. Maybe change your pampers?
> 
> Bye
> 
> Mild Shock schrieb:
>> Hi,
>>
>> Micro Penis is worse than Sleepy Joe. He
>> probably only believes the existence of a
>> hammer, when you hit him on the head with
>>
>> a hammer. Currently Micro Penis is sitting
>> there and shitting his pants it seems.
>>
>> Bye
>>
>>  > stop polluting this group with nonsense,
>>  > you stupid unemployed former it-supporter.
>>  > I shit in your shaders. You were talking
>>  > about AI. Those ryzen AI laptops are for fools.
>>
>> Mild Shock schrieb:
>>> Hi,
>>>
>>> It seems micro penis has a real existential
>>> crisis right now. An alice in wonderland moment,
>>> falling down a rabit whole. Well no wonder
>>>
>>> micro penis lives under a rock and has never
>>> heard of the small model revolution that goes
>>> hand in hand with the AI laptop revolution.
>>>
>>> Here is a test, running deepseek locally on
>>> a budget laptop (via LM Studio, oMLX, etc..):
>>>
>>> qwen3.5-9b-deepseek-v4-flash
>>>
>>> Q: Well there is a formidable horse race going on.
>>> Given the danger that I compare apples with oranges.
>>> It is still interesting too see how the Al laptop
>>> landscape is forming.
>>>
>>> Thought for 1 minutes 20 seconds
>>>
>>> A: You hit on a really crucial point in the Al economy:
>>> the tension between cloud consumption and edge ownership.
>>> When you compare a $0.50 per 1k-token API call with a
>>> $2,000 laptop that runs Qwen3.5 locally for free
>>> (electricity aside), it's not strictly apples-to-oranges
>>> because one is a service and the other is an asset. But
>>> the implications for how we use Al are massive.
>>>
>>> Bye
>>>
>>> Mild Shock schrieb:
>>>> Hi,
>>>>
>>>> It seems micro penis struggles with mobile
>>>> grade GPU concept. Whats the difference
>>>> between a mobile grade GPU and non-mobile grade
>>>>
>>>> GPU? You know the **M** in **Readeon 860M**
>>>> means Mobile! Here is a comparison:
>>>>
>>>> **Mobile GPU:**
>>>>
>>>> Energy Consuption: Low
>>>> Device Memory: AUP (accelerator unit processor,
>>>>     shares memory with CPU, no VRAM)
>>>> Cooling System: Fewer or no fans
>>>>
>>>> **Non-Mobile GPU:**
>>>>
>>>> Energy Consuption: High
>>>> Device Memory: DUP (discret unit processor,
>>>>     has its own VRAM)
>>>> Cooling System: A lot of fans or other cooling
>>>>
>>>> Bye
>>>>
>>>> BTW: Here are some results for:
>>>>
>>>> 11.4 Giga Lips with a Budget Laptop
>>>> https://github.com/Jean-Luc-Picard-2021/gigabudget
>>>>
>>>> On a smartphone, namely Redmi Note 14 Pro+:
>>>>
>>>> 1 Shader
>>>> 1983 ms
>>>>
>>>> 4096 Shaders
>>>> 16253 ms
>>>>
>>>> The phone uses a Snapdragon 7s Gen 3
>>>>
>>>> Mild Shock schrieb:
>>>>> Hi,
>>>>>
>>>>> Micro Penis the putin payed troll, is now
>>>>> on the payment list of overpriced NVIDIA as
>>>>> well. He cannot get over the concept of a
>>>>>
>>>>> Shoe String Budget:
>>>>>
>>>>> "According to Darren Aronofsky’s debut
>>>>> 1998 film Pi, “everything around us can
>>>>> be represented and understood through numbers”,
>>>>> from the stock market to the “wax and wane
>>>>> of caribou populations”. But, ironically,
>>>>> the film’s own numerical facts feel particularly
>>>>> inexplicable. It was made on a budget of just
>>>>> $60,000, which is less a shoestring and more
>>>>> just the aglet at the end of a frayed lace.
>>>>> To put that in to perspective, 1999’s The
>>>>> Matrix – similarly based around the dystopian
>>>>> danger of AI – may have been slightly slicker
>>>>> and sexier, but also was made for $60m, a
>>>>> thousand times more buck for a thousand
>>>>> times less bang. Plus, it means that its
>>>>> profit margin was huge. As Variety’s headline
>>>>> following its release put it, ‘”π=$1,000,000!”
>>>>> https://www.vice.com/en/article/pi-soundtrack-20-years-aronofsky-aphex-twin-autechre/ 
>>>>>
>>>>>
>>>>> 04 Bucephalus Bouncing Ball
>>>>> https://www.youtube.com/watch?v=Ez6xDGTFswQ
>>>>>
>>>>> Bye
>>>>>
>>>>> Loman Barabashev schrieb:
>>>>>  > I have a micro penis and my brain explodes
>>
> 

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

#347894 — nothing gets blocked except your brain [LPDDR5X-RAM] (Re: herpes blister rossy boy is confused)

Hi,

Complete micro penis moron repeats his nonsense
over and over? Although I am told him already
about unified memory architecture (UMA) convergence:

 > to the embedded gpu, blocked by the speed of the cpu

Ever heard of Dual-Channel-RAM in the
new AI laptops? Whats wrong with you moron?
I mean I wrote LPDDR5X-RAM here, didn't I?

 >> Arbeitsspeicher 32 GB Arbeitsspeichertyp LPDDR5X-RAM

For Ryzen AI systems, using RAM in dual-channel
mode is essential. Since local AI models, integrated
graphics units (iGPUs), and processors all access
the same memory pool, dual-channel provides double
the memory bandwidth.

This drastically reduces latencies. Dual-channel
memory (such as DDR5-5600 or LPDDR5x-8000) is
strictly required, especially for the latest
Ryzen AI 300 laptops (Strix Point) or high-end
Ryzen AI Max systems, to fully exploit the maximum
performance values (TOPS) of the Neural Processing
Unit (NPU) and the integrated Radeon graphics.

Bye

Mild Shock schrieb:
> Hi,
> 
> herpes blister rossy boy is confused.
> One more idiot on the loose that
> cannot do research of AI laptop prices.
> 
> Here you idiots:
> 
> Acer Aspire 14 AI
> https://www.digitec.ch/de/s1/product/acer-aspire-14-ai-14-1000-gb-32-gb-ch-amd-ryzen-ai-7-350-notebook-65210813 
> 
> 
> Price: 999.–
> Prozessortyp AMD Ryzen AI 7 350
> Grafikkarten Modell Radeon 860M
> Onboard Arbeitsspeicher 32 GB
> Arbeitsspeichertyp LPDDR5X-RAM
> 
> So its even not the case that RAM prices
> have affected AI laptop prices that much.
> 
> Bye
> 
> BTW: The acer company is a taiwan company.
> The above laptop from the aspire series,
> is a little thicker than the one from the
> 
> swift series:
> 
> Acer Aspire One – Acer's mid to high-end personal-use laptop
> Acer Swift – A series of mid to high-end ultra-portable notebooks
> 
> https://en.wikipedia.org/wiki/Acer_Inc.
> 
> Ross Finlayson schrieb:
>  > On 07/11/2026 05:25 AM, Loman Barabashev wrote:
>  >> Mild Shock wrote:
>  >>
>  >>> Hi,
>  >>>
>  >>> 11.4 Giga Lips with a Budget Laptop
>  >>> https://github.com/Jean-Luc-Picard-2021/gigabudget
>  >>>
>  >>> Budget Laptop means ~1000 USD.
>  >>> Thats not big money. The Mac Neo is even better only ~500 USD.
>  >>
>  >> you stinking sack of rocks, you can't read your own redundant links. 
> Watch
>  >> the prices for the Ryzen AI laptops. Fucking idiot. Not worth the price
>  >> for what they give in AI. Those are embedded cpu/gpu cretin, you don't
>  >> need to read more.
>  >>
>  >
>  > Shut Up, "Burse".
> 
> Mild Shock schrieb:
>> Hi,
>>
>> Hey micro penis, your shitting start
>> smelling. Maybe change your pampers?
>>
>> Bye
>>
>> Mild Shock schrieb:
>>> Hi,
>>>
>>> Micro Penis is worse than Sleepy Joe. He
>>> probably only believes the existence of a
>>> hammer, when you hit him on the head with
>>>
>>> a hammer. Currently Micro Penis is sitting
>>> there and shitting his pants it seems.
>>>
>>> Bye
>>>
>>>  > stop polluting this group with nonsense,
>>>  > you stupid unemployed former it-supporter.
>>>  > I shit in your shaders. You were talking
>>>  > about AI. Those ryzen AI laptops are for fools.
>>>
>>> Mild Shock schrieb:
>>>> Hi,
>>>>
>>>> It seems micro penis has a real existential
>>>> crisis right now. An alice in wonderland moment,
>>>> falling down a rabit whole. Well no wonder
>>>>
>>>> micro penis lives under a rock and has never
>>>> heard of the small model revolution that goes
>>>> hand in hand with the AI laptop revolution.
>>>>
>>>> Here is a test, running deepseek locally on
>>>> a budget laptop (via LM Studio, oMLX, etc..):
>>>>
>>>> qwen3.5-9b-deepseek-v4-flash
>>>>
>>>> Q: Well there is a formidable horse race going on.
>>>> Given the danger that I compare apples with oranges.
>>>> It is still interesting too see how the Al laptop
>>>> landscape is forming.
>>>>
>>>> Thought for 1 minutes 20 seconds
>>>>
>>>> A: You hit on a really crucial point in the Al economy:
>>>> the tension between cloud consumption and edge ownership.
>>>> When you compare a $0.50 per 1k-token API call with a
>>>> $2,000 laptop that runs Qwen3.5 locally for free
>>>> (electricity aside), it's not strictly apples-to-oranges
>>>> because one is a service and the other is an asset. But
>>>> the implications for how we use Al are massive.
>>>>
>>>> Bye
>>>>
>>>> Mild Shock schrieb:
>>>>> Hi,
>>>>>
>>>>> It seems micro penis struggles with mobile
>>>>> grade GPU concept. Whats the difference
>>>>> between a mobile grade GPU and non-mobile grade
>>>>>
>>>>> GPU? You know the **M** in **Readeon 860M**
>>>>> means Mobile! Here is a comparison:
>>>>>
>>>>> **Mobile GPU:**
>>>>>
>>>>> Energy Consuption: Low
>>>>> Device Memory: AUP (accelerator unit processor,
>>>>>     shares memory with CPU, no VRAM)
>>>>> Cooling System: Fewer or no fans
>>>>>
>>>>> **Non-Mobile GPU:**
>>>>>
>>>>> Energy Consuption: High
>>>>> Device Memory: DUP (discret unit processor,
>>>>>     has its own VRAM)
>>>>> Cooling System: A lot of fans or other cooling
>>>>>
>>>>> Bye
>>>>>
>>>>> BTW: Here are some results for:
>>>>>
>>>>> 11.4 Giga Lips with a Budget Laptop
>>>>> https://github.com/Jean-Luc-Picard-2021/gigabudget
>>>>>
>>>>> On a smartphone, namely Redmi Note 14 Pro+:
>>>>>
>>>>> 1 Shader
>>>>> 1983 ms
>>>>>
>>>>> 4096 Shaders
>>>>> 16253 ms
>>>>>
>>>>> The phone uses a Snapdragon 7s Gen 3
>>>>>
>>>>> Mild Shock schrieb:
>>>>>> Hi,
>>>>>>
>>>>>> Micro Penis the putin payed troll, is now
>>>>>> on the payment list of overpriced NVIDIA as
>>>>>> well. He cannot get over the concept of a
>>>>>>
>>>>>> Shoe String Budget:
>>>>>>
>>>>>> "According to Darren Aronofsky’s debut
>>>>>> 1998 film Pi, “everything around us can
>>>>>> be represented and understood through numbers”,
>>>>>> from the stock market to the “wax and wane
>>>>>> of caribou populations”. But, ironically,
>>>>>> the film’s own numerical facts feel particularly
>>>>>> inexplicable. It was made on a budget of just
>>>>>> $60,000, which is less a shoestring and more
>>>>>> just the aglet at the end of a frayed lace.
>>>>>> To put that in to perspective, 1999’s The
>>>>>> Matrix – similarly based around the dystopian
>>>>>> danger of AI – may have been slightly slicker
>>>>>> and sexier, but also was made for $60m, a
>>>>>> thousand times more buck for a thousand
>>>>>> times less bang. Plus, it means that its
>>>>>> profit margin was huge. As Variety’s headline
>>>>>> following its release put it, ‘”π=$1,000,000!”
>>>>>> https://www.vice.com/en/article/pi-soundtrack-20-years-aronofsky-aphex-twin-autechre/ 
>>>>>>
>>>>>>
>>>>>> 04 Bucephalus Bouncing Ball
>>>>>> https://www.youtube.com/watch?v=Ez6xDGTFswQ
>>>>>>
>>>>>> Bye
>>>>>>
>>>>>> Loman Barabashev schrieb:
>>>>>>  > I have a micro penis and my brain explodes
>>>
>>
> 

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

#347895 — flogging a dead horse PCI VRAM graphic cards (Re: nothing gets blocked except your brain [LPDDR5X-RAM])

Hi,

Micro penis is flogging the dead horse
PCI VRAM graphic card. If you combine unified
memory architecture (UMA) with CMOS 2.0

you can build amazing things, a PCI
interface to a VRAM never can do. For
example you could also place GPUs and

CPU cores on a die side by side, a card
need to be GPU only, and of course huge
amounts of RAM. And then stack the

things vertically somehow, like the
3.5D advanced packaging:

"Das Substrat (organisches Package) stellt
die unterste Ebene dar. Darauf sitzt der
passive Silicon Interposer als Chip on
Wafer on Substrate (CoWoS). Auf dem Silicon
Interposer sitzen einerseits die IODs, auf
denen sich wiederum die XCDs und CCDs befinden
und die HBM3-Speicherchips. Dummy-Chips neben
den XCDs und CCDs füllen die Lücken, ein
sogenanntes Carrier Silicon bringt die Chips
auf die gleiche Höhe wie die HBM3-Speicherchips
und alles wird mit einem Heatspreader abgedeckt."
https://www.hardwareluxx.de/index.php/news/hardware/grafikkarten/62454-amd-instinct-mi300-familie.html

Bye

Mild Shock schrieb:
> Hi,
> 
> Complete micro penis moron repeats his nonsense
> over and over? Although I am told him already
> about unified memory architecture (UMA) convergence:
> 
>  > to the embedded gpu, blocked by the speed of the cpu
> 
> Ever heard of Dual-Channel-RAM in the
> new AI laptops? Whats wrong with you moron?
> I mean I wrote LPDDR5X-RAM here, didn't I?
> 
>  >> Arbeitsspeicher 32 GB Arbeitsspeichertyp LPDDR5X-RAM
> 
> For Ryzen AI systems, using RAM in dual-channel
> mode is essential. Since local AI models, integrated
> graphics units (iGPUs), and processors all access
> the same memory pool, dual-channel provides double
> the memory bandwidth.
> 
> This drastically reduces latencies. Dual-channel
> memory (such as DDR5-5600 or LPDDR5x-8000) is
> strictly required, especially for the latest
> Ryzen AI 300 laptops (Strix Point) or high-end
> Ryzen AI Max systems, to fully exploit the maximum
> performance values (TOPS) of the Neural Processing
> Unit (NPU) and the integrated Radeon graphics.
> 
> Bye
> 
> Mild Shock schrieb:
>> Hi,
>>
>> herpes blister rossy boy is confused.
>> One more idiot on the loose that
>> cannot do research of AI laptop prices.
>>
>> Here you idiots:
>>
>> Acer Aspire 14 AI
>> https://www.digitec.ch/de/s1/product/acer-aspire-14-ai-14-1000-gb-32-gb-ch-amd-ryzen-ai-7-350-notebook-65210813 
>>
>>
>> Price: 999.–
>> Prozessortyp AMD Ryzen AI 7 350
>> Grafikkarten Modell Radeon 860M
>> Onboard Arbeitsspeicher 32 GB
>> Arbeitsspeichertyp LPDDR5X-RAM
>>
>> So its even not the case that RAM prices
>> have affected AI laptop prices that much.
>>
>> Bye
>>
>> BTW: The acer company is a taiwan company.
>> The above laptop from the aspire series,
>> is a little thicker than the one from the
>>
>> swift series:
>>
>> Acer Aspire One – Acer's mid to high-end personal-use laptop
>> Acer Swift – A series of mid to high-end ultra-portable notebooks
>>
>> https://en.wikipedia.org/wiki/Acer_Inc.
>>
>> Ross Finlayson schrieb:
>>  > On 07/11/2026 05:25 AM, Loman Barabashev wrote:
>>  >> Mild Shock wrote:
>>  >>
>>  >>> Hi,
>>  >>>
>>  >>> 11.4 Giga Lips with a Budget Laptop
>>  >>> https://github.com/Jean-Luc-Picard-2021/gigabudget
>>  >>>
>>  >>> Budget Laptop means ~1000 USD.
>>  >>> Thats not big money. The Mac Neo is even better only ~500 USD.
>>  >>
>>  >> you stinking sack of rocks, you can't read your own redundant 
>> links. Watch
>>  >> the prices for the Ryzen AI laptops. Fucking idiot. Not worth the 
>> price
>>  >> for what they give in AI. Those are embedded cpu/gpu cretin, you 
>> don't
>>  >> need to read more.
>>  >>
>>  >
>>  > Shut Up, "Burse".
>>
>> Mild Shock schrieb:
>>> Hi,
>>>
>>> Hey micro penis, your shitting start
>>> smelling. Maybe change your pampers?
>>>
>>> Bye
>>>
>>> Mild Shock schrieb:
>>>> Hi,
>>>>
>>>> Micro Penis is worse than Sleepy Joe. He
>>>> probably only believes the existence of a
>>>> hammer, when you hit him on the head with
>>>>
>>>> a hammer. Currently Micro Penis is sitting
>>>> there and shitting his pants it seems.
>>>>
>>>> Bye
>>>>
>>>>  > stop polluting this group with nonsense,
>>>>  > you stupid unemployed former it-supporter.
>>>>  > I shit in your shaders. You were talking
>>>>  > about AI. Those ryzen AI laptops are for fools.
>>>>
>>>> Mild Shock schrieb:
>>>>> Hi,
>>>>>
>>>>> It seems micro penis has a real existential
>>>>> crisis right now. An alice in wonderland moment,
>>>>> falling down a rabit whole. Well no wonder
>>>>>
>>>>> micro penis lives under a rock and has never
>>>>> heard of the small model revolution that goes
>>>>> hand in hand with the AI laptop revolution.
>>>>>
>>>>> Here is a test, running deepseek locally on
>>>>> a budget laptop (via LM Studio, oMLX, etc..):
>>>>>
>>>>> qwen3.5-9b-deepseek-v4-flash
>>>>>
>>>>> Q: Well there is a formidable horse race going on.
>>>>> Given the danger that I compare apples with oranges.
>>>>> It is still interesting too see how the Al laptop
>>>>> landscape is forming.
>>>>>
>>>>> Thought for 1 minutes 20 seconds
>>>>>
>>>>> A: You hit on a really crucial point in the Al economy:
>>>>> the tension between cloud consumption and edge ownership.
>>>>> When you compare a $0.50 per 1k-token API call with a
>>>>> $2,000 laptop that runs Qwen3.5 locally for free
>>>>> (electricity aside), it's not strictly apples-to-oranges
>>>>> because one is a service and the other is an asset. But
>>>>> the implications for how we use Al are massive.
>>>>>
>>>>> Bye
>>>>>
>>>>> Mild Shock schrieb:
>>>>>> Hi,
>>>>>>
>>>>>> It seems micro penis struggles with mobile
>>>>>> grade GPU concept. Whats the difference
>>>>>> between a mobile grade GPU and non-mobile grade
>>>>>>
>>>>>> GPU? You know the **M** in **Readeon 860M**
>>>>>> means Mobile! Here is a comparison:
>>>>>>
>>>>>> **Mobile GPU:**
>>>>>>
>>>>>> Energy Consuption: Low
>>>>>> Device Memory: AUP (accelerator unit processor,
>>>>>>     shares memory with CPU, no VRAM)
>>>>>> Cooling System: Fewer or no fans
>>>>>>
>>>>>> **Non-Mobile GPU:**
>>>>>>
>>>>>> Energy Consuption: High
>>>>>> Device Memory: DUP (discret unit processor,
>>>>>>     has its own VRAM)
>>>>>> Cooling System: A lot of fans or other cooling
>>>>>>
>>>>>> Bye
>>>>>>
>>>>>> BTW: Here are some results for:
>>>>>>
>>>>>> 11.4 Giga Lips with a Budget Laptop
>>>>>> https://github.com/Jean-Luc-Picard-2021/gigabudget
>>>>>>
>>>>>> On a smartphone, namely Redmi Note 14 Pro+:
>>>>>>
>>>>>> 1 Shader
>>>>>> 1983 ms
>>>>>>
>>>>>> 4096 Shaders
>>>>>> 16253 ms
>>>>>>
>>>>>> The phone uses a Snapdragon 7s Gen 3
>>>>>>
>>>>>> Mild Shock schrieb:
>>>>>>> Hi,
>>>>>>>
>>>>>>> Micro Penis the putin payed troll, is now
>>>>>>> on the payment list of overpriced NVIDIA as
>>>>>>> well. He cannot get over the concept of a
>>>>>>>
>>>>>>> Shoe String Budget:
>>>>>>>
>>>>>>> "According to Darren Aronofsky’s debut
>>>>>>> 1998 film Pi, “everything around us can
>>>>>>> be represented and understood through numbers”,
>>>>>>> from the stock market to the “wax and wane
>>>>>>> of caribou populations”. But, ironically,
>>>>>>> the film’s own numerical facts feel particularly
>>>>>>> inexplicable. It was made on a budget of just
>>>>>>> $60,000, which is less a shoestring and more
>>>>>>> just the aglet at the end of a frayed lace.
>>>>>>> To put that in to perspective, 1999’s The
>>>>>>> Matrix – similarly based around the dystopian
>>>>>>> danger of AI – may have been slightly slicker
>>>>>>> and sexier, but also was made for $60m, a
>>>>>>> thousand times more buck for a thousand
>>>>>>> times less bang. Plus, it means that its
>>>>>>> profit margin was huge. As Variety’s headline
>>>>>>> following its release put it, ‘”π=$1,000,000!”
>>>>>>> https://www.vice.com/en/article/pi-soundtrack-20-years-aronofsky-aphex-twin-autechre/ 
>>>>>>>
>>>>>>>
>>>>>>> 04 Bucephalus Bouncing Ball
>>>>>>> https://www.youtube.com/watch?v=Ez6xDGTFswQ
>>>>>>>
>>>>>>> Bye
>>>>>>>
>>>>>>> Loman Barabashev schrieb:
>>>>>>>  > I have a micro penis and my brain explodes
>>>>
>>>
>>
> 

[toc] | [prev] | [standalone]

Page 2 of 2 — ← Prev page 1 [2]

Back to top | Article view | sci.logic

csiph-web