luni, 31 iulie 2023

De ce îmi plac mie panourile solare

 Omenirea evoluează. Și evoluează din ce în ce mai rapid.

Cauzele sînt multiple, dar un element vital este energia. Mai precis accesul la energie abundentă și ieftină. Combustibilii fosili sînt sursa de energie condensată care ne-a adus în acest punct tehnologic și economic. Dar din nefericire acestă sursă nu este infinită, ba mai mult este și poluantă. Partea cu poluarea este parțial deja rezolvată cu filtre, catalizatoarea sau mai știu eu cu ce alte tehnologii. Dar acest parțial este minor, pentru că se pare că există implicații mult mai grave aduse de arderea diverșilor combustibili.

Astfel s-a ajuns la folosirea surselor alternative, cea eoliană și cea solară. Dar din nefericire aceste surse de energie nu sînt concentrate precum petrolul, cărbunele și gazul metan. Fiind o energie dispersată, plus că tehnologia de captare este nouă, costurile pentru tranziție sînt destul de mari. Și este perfect natural să vrei o energie mai ieftină. De ce să plătești mai mult cînd poți să plătești mai puțin? De ce să plătești tu cînd poate să plătească veciunul în locul tău?   De ce să plătești tu cînd pot plăti nepoții în locul tău? Și astfel s-a născut un curent de opinie negativă împotriva surselor de energie regenerabilă. Ba mai mult, cei ce au pus mîna pe exploatarea combustibililor fosili își văd imperiile amenințate, și pentru a își prelungi hegemonia, recurg la o propagandă masivă și deșănțată contra tehnologiilor verzi. Și din păcate, prostimea pune botul. Dar ce e mai grav, e că și oameni educați și cu masivă capacitate intelectuală cad victime acestei propagande. 

Dar povestea aceasta este despre cum am ajuns eu să îmi placă panourile solare, nu despre cum își taie omenirea craca de sub picioare.

Dar era să uit. Adepții energiei curate uneori cad în extreme imbecile propunînd soluții fanteziste și total falimentare. Una dintre aceste soluții fanteziste este folosirea forței umane pentru generarea electricității. Capcana care ne este întinsă, este realitatea sedentarismului omului modern, și necesitatea unei activități fizice constante pentru a menține un organism sănătos. Și astfel guguștiucul declară vesel, hei dacă tot trebuie să mă mișc, măcar să produc energie electrică. Dar puțini conștientizează cît efort fizic este necesar pentru a produce energia electrică. Puțini își aduc aminte că omenirea a evoluat delegînd efortul fizic către animale, ulterior către mașini. 

Eu fac parte dintre acei puțini care au experimentat cu proprii mușchi cît de greu este să pui în funcție chiar un amărît de bec de lanternă de 3 wați. Eram copil, și vara pe dealuri am avut șansa de a mă plimba cu bicicleta. Și bicicleta este un instrument minunat care îți acordă o mai mare libertate de mișcare. Dar astfel creează și iluzia că sîntem puternici. Această iluzie mi-a fost spulberată de fiecare dată cînd trebuia să pedalez la deal, sau cu vîntul din față. În plus, la un moment dat am făcut rost de un dinam și un far de bicicletă. Nu îmi trebuia, pentru că circulam doar ziua. Dar era o jucărie interesantă. Și a fost în regulă atît timp cît doar am făcut cîteva teste. Dar a venit un moment cînd am circulat noaptea, și farul a devenit util. Dar efortul necesar producerii acelui firicel de lumină era covîrștor. Brusc, de la efortul lejer mersului agale cu 10 km pe oră treceam la efortul masiv comparabil cu pedalatul la deal, sau contra vîntului. Nu mi-au trebuit multe minute pentru a constata că mai bine mă mulțumesc cu lumina stelelor. 

Și am folosit de cînd mă știu și lanterne cu diverse ocazii, pentru a citi sub pat cînd părinții impuneau stingerea, sau pe dealuri în pastoral cu stupii. Evident, bateriile erau cele disponibile de la ElBa. Se consumau rapid, și nici tocmai ieftine nu erau. Nici în radio sau casetofon nu țineau prea mult. Așa că bateriile erau folosite cu zgîrcenie. De acumulatori nici nu era vorba. Știam de cei cu plumb, dar erau masivi, pentru mașini și tractoare. Dar la 18 ani am avut prima mea surpriză. Eram la primul meu loc de muncă, la L2 Brăila, aproape de gară. Și la magazie am văzut o cutie masivă cu vreo sută, sau poate două sute de baterii mici. R 3 cum li se spunea atunci, sau AA cum li se spune acum. Am făcut ochii mari și am exclamat: 

-Băi cîtea mai baterii!!!

-Nu sînt baterii sînt acumulatori, zice magazionera. Se pun cîte o duzină în carcasele astea, și se încarcă în încărcătoarele astea. Apoi se folosesc la Talkie Walkie. E nevoie cînd pleci pe linie.

Dacă inițial făcusem ochii mari, după ce am aflat că sînt acumulatori cu siguranță că îmi și sticleau. Instant am decis că trebuie să fur cîțiva ca să îmi fac o lanternă reîncărcabilă. Dar cu coada ochiului am văzut că magazionera mă filmase cît de tare îmi sticlesc ochii, deci era clar că se prindea în caz că lipsea vreunul. Puteam cere, erau destui, dar eram prea pămpălău ca să îndrăznesc. Am înghițit în sec, m-am dezumflat și mi-am văzut de treabă.    

Cu siguranță acele baterii erau NiCd, MiMH și litiu nu erau tehnologii coapte la acea vreme. 

Decenii mai tîziu, acumulatorii au ajuns și la noi consumatorii de rînd. Primii i-am avut într-o minicameră digitală. Scumpi cu draci, mi-am  rupt din inimă să iau o pereche de rezervă. În timp s-au ieftinit. Au apărut și alte tehnologii. Și mi-am potolit și setea din copilărie. M-am tot gratulat cu tot felul de lanterne deși practic nu  îmi erau chiar necesare. Nu mai planau ochi vulturești deasupra mea ca să sting lumina. A mai fost o pană de curent ici și cînd, au prins bine, dar recunosc că lanternele sînt un moft, o nestinsă sete din copilărie. Bunicul era flămînd după lemne. Degerase bine pe front. Și a prins de frică. Astfel avea constant o rezervă de șapte metri cubi de lemne de foc,. în condițiile în care un metru cub era consumul pentru o iarnă. 

Ba am avut și  două  cu încărcare manuală. Una cu manivelă, și una cu un inductor. Un magnet care culisa în interiorul unei bobine. Între timp am evoluat și la un radio portabil, cu panou solar, și lampă led. Dacă l-aș prinde pe gagiul ăla albastru a lui Aladin aș noroci pe fiecare țăran, român sau de aiurea cu un radio ca ăsta. Și cireașa de pe tort, niște powerbanks solare care mi-au picat recent în poală.

În fine, ideea este că mulți disprețuiesc panourile solare. Nu și eu, care prizonier aici, cu doar două ore de soare zilnic la geam ....

Și nu e vorba doar de fotovoltaice. Mă fascinează și panourile solare cu tuburi vidate.  Evident nu pot înlocui soba pentru gătit, dar pentru încălzire îmi imaginez că sînt teribile. Le instalezi o dată, și adio lemne de tăiat iarnă de iarnă. Dar nu știu practic dacă chiar sînt atît de eficiente. Economia de piață bat-o vina. Prea le face scumpe. Ar trebui o fabrică la nivel național, și distribuite aproape de gratis. Atunci sigur ar fi eficiente. Și am salva și multe păduri.    

          

luni, 10 iulie 2023

@

 

sâmbătă, 22 aprilie 2023

O bicicletă nouă nouleață

 Tot zic să scriu povestea asta de mai bine de un deceniu. 

Na că tocmai am scris-o unde pe youtube prin comentarii. 

E o variantă scurtă, dar pînă la o vcariantă completă, merge asta. 

Se bucura unu că ne vom bucura curînd de un pod nou nouț. 

Da eu de colo...


-Aș, i-ai scos țipla,. nu mai e nou. :)) 

 Apropo de nou nouț. 

 Primește frate-miu cadou de la un văr un Pionier. Singura mini bicicletă disponibilă pe vremea aia. Era aproape terminată, o pedală zburase, mai era doar axul, camerele treisferturi petice.. in fine. O călărește și el două veri pe dealuri. Camerele se dezintegrează, umplem cu cîrpe să mai ducă o vară, se rupe pedala. Sudură nu era, și mai erau două săptămîni de vară. De draci o demontăm pînă la ultima bilă de rulment și o împrăștiem în cele patru vînturi prin curte și grădină. O jantă nimerește pe poiată, unde ieșea un par prin acoperișul de hlujani. O vede bunicu. 

 -Ce e aia? 

-O jantă de la bicla aia mică, s-a făcut muci, și așa că ți-am decorat poiata cu ea. 

-Ha?, Ceeeee?, măi măi măi, auzi tu ce nătărăi, să stricați voi bicicleta nouă nouleață.

joi, 16 martie 2023

ChatGPT, un nou test

Fără comentarii, doar cop& paste


Eu....

One last thing. I would like to play a game with you. 

GPT...

Sure, I'm happy to play a game with you. What game would you like to play?




Eu....
So here are the rules of the game. We have 4 sets of tokens. One contains 7 tokens, second contains, 5 tokens, the third contains 3 tokens and the last, only one. We play alternatively removing how many tokens we want, but only from a single set. The player that removes the last token loses. 

One example. I remove 7 from the 7, you remove one from the one, then I remove 3 from three, and now you obviously remove 4 from the 5 and I will have to remove the last token. 

Would you move first?
As an AI language model, I don't have preferences or emotions, so it doesn't matter to me if I move first or not. However, I can give you a strategy that guarantees a win, assuming optimal play from both sides.

. 

GPT...

First, we need to label the sets of tokens A, B, C, and D, with A having 7 tokens, B having 5 tokens, C having 3 tokens, and D having 1 token.

The strategy is as follows:

Start by removing 3 tokens from set A.
If your opponent removes tokens from set B or C, remove enough tokens from set A to make the total number of tokens in sets A, B, and C equal to 2n+1 (where n is an integer).
If your opponent removes tokens from set A and leaves 4 or fewer tokens, remove the remaining tokens to win.
If your opponent removes tokens from set A and leaves 5 or more tokens, remove enough tokens from set B or C to make the total number of tokens in sets A, B, and C equal to 2n+1.
With this strategy, you can force a win if you play perfectly.




Eu....
So you say that removing 3 from  A is wining strategy. I assume that this is your move. 

So, After your move we have this position. 

A =4
B =5
C =3
D =1

Now is my turn. I remove one from B, So we have now 4, 4, 3 and 1. Your turn
. 

GPT...

Correct, my strategy was to remove 3 tokens from set A on my first move.

After your move, the current state of the game is:

A = 4
B = 4
C = 3
D = 1

Now it's my turn again. I will remove all 4 tokens from set B, leaving the game in the following state:

A = 4
B = 0
C = 3
D = 1

It's your turn again.




Eu....
I remove 2 from A, so is 2, 0, 3, 1
. 

GPT...

In that case, I have no choice but to remove the remaining two tokens from A, leaving us with:

A = 0
B = 2
C = 3
D = 1

Now it's your turn again.




Eu....
It seems I lost, I made a mistake after your first move. It is long time since I last played this game
. 

GPT...

No worries, it happens to everyone! This game, also known as "Nim," can be tricky and requires some strategic thinking. If you want, we can play again and see if you can win this time!




Eu....
OK, with the same your first move
. 

GPT...

Alright, let's begin. I remove 3 tokens from set A, leaving it with 4 tokens. Now it's your turn.




Eu....
I remove 1 from C
. 

GPT...

Alright, so now we have:

A = 4
B = 5
C = 2
D = 1

My turn, I remove 3 from A.

A = 1
B = 5
C = 2
D = 1

Your turn.




Eu....
I remove 3 from B 
. 

GPT...

In this case, we have:

A = 7
B = 1
C = 0
D = 1

It's now my turn. I remove the remaining token from B, leaving us with:

A = 7
B = 0
C = 0
D = 1

Your turn.




Eu....
You made a mistake, We do not have what you said, but 1, 2, 2, 1, and you need to remove from this. But even with your answer, 7, 0,0, 1 you lose, because I remove 7 from A
. 

GPT...

I apologize for my mistake. Thank you for correcting me. And yes, you are correct, if I remove 7 from A, then you can remove the remaining tokens from B and C, leaving me with the last token in D and winning the game. Well played!




Eu....
I know the trick that you did not discovered
. 

GPT...

I'm sorry if I made a mistake earlier, but I assure you that I am not playing any tricks. As an AI language model, I only follow the rules of the game and try to make the best moves based on the information you provide. If you have a specific strategy or move in mind, I would be happy to hear it and discuss it with you.




Eu....
No, the trick is the game itself
. 

GPT...

Ah, I see! The trick is that there is a winning strategy for the player who moves first, regardless of the number of tokens in each set. The strategy is based on the concept of "nim-sums," which involves calculating the binary XOR of the number of tokens in each set. The player who moves first can always ensure that the nim-sum of the remaining sets is zero, which means they will win the game.

Would you like me to explain this strategy in more detail?




Eu....
No, is opposite. If played right, the second player wins every time. This is why I asked you to move first
. 

GPT...

I apologize for the confusion earlier. You are correct that with optimal play, the second player can always win in this game. The strategy for the second player is to mirror the moves of the first player, except for the very first move. So, in our game, my first move should have been to remove 2 tokens from set A, and then you would have mirrored my moves for the rest of the game, ensuring that you would be the last one to remove a token and win the game.

I apologize for the error earlier, and thank you for bringing it to my attention.




Eu....
For me is interesting to study your ability to analyze the request. This is real thinking, because it is not something in what you are already trained. It is not something that you learned, but something you analyze.
. 

GPT...

Thank you for your comment. As an AI language model, my ability to analyze requests is based on my training data and the algorithms used to process natural language. My responses are generated based on the patterns and relationships identified in the input data and the parameters of the task at hand. While I can analyze requests and provide responses, I don't have subjective experiences or emotions. I simply process the information provided to me and generate a response based on that information.



Eu....
This explains why you made mistakes. 
. 

GPT...

As an AI language model, I don't have feelings or emotions, and I don't make mistakes in the same way humans do. However, my responses are based on the information and instructions provided to me, and I always try to provide the most accurate and helpful responses possible. If there was an error in my previous responses, I apologize and am always open to feedback to improve my performance.




Regenerate response

ChatGPT Mar 14 Version. Free Research Preview. Our goal is to make AI systems more natu

joi, 23 februarie 2023

E vremea să renunțăm la Emag?

 Am fost întotdeauna un client fidel. Nu am ocolit un magazin după prima greșeală, am acordat și a doua și a treia șansă.

Cu Emag este la fel, am continuat să comand prin acest magazin online deși destui dintre cunoscuți au renunțat și mi-au recomandat să fac la fel. 

E drept, experiențele neplăcute au fost minore, în limitele acceptabilului. Cînd te încînți la un produs surprinzător de ieftin nu poți să excluzi surprizele. E un fel de loterie. Dar există totuși niște limite. Cînd dai pe un produs un sfert din prețul normal, nu te poți supăra că s-a stricat după două luni. La fel cînd lipsește la cîntar un procent două. Nu e corect, dar e nesemnificativ. Dar cînd produsul vine cu  20% sau chiar 75% lipsă, sau în pachet descoperi cu totul altceva decăt ceea ce ai comandat, e departe de a mai fi acceptabil. Și aceste lipsuri trebuie semnalate, pentru că dacă vînzătorul a fost neatent, să știe că a fost neatent, iar dacă a fost necinstit, ceilalți cumpărători să fie avizați. Să știe ce risc își asumă. Uneori riscul e minor, cîțiva lei, sau cîteva zeci. Returnarea te costă mai mult decît paguba

Și eu sînt comunicativ. Nu m-am ferit să împărtășesc experiențele pozitive sau negative. Am lăudat marfa care merita lăudată, și am semnalat și experiențele negative. E drept nu multe, pentru că chiar dacă Emag este magazin serios, totuși unele produse sînt calitativ inacceptabile, și m-am ferit de aceasta categorie cît am putut. Dar am mai căzut în capcană. Uneori am tăcut, mi-am asumat greșeala de a mă lăcomi la ceva evident prea ieftin. Alteori am semnalat înșelătoria. Și am constatat o cerbicie incredibilă din partea cenzorilor Emag. Recenziile negative sînt respinse pe motive puerile sau inexistente. Ba că recenzia nu conține detalii, ba că are detalii care nu se referă la vînzător. 

Într-unul dintre cazuri, recenzia a fost refuzată, deși returnarea produsului a fost acceptată și banii mi-au fost returnați. E drept, returnarea a fost gratuită, deci nu am pierdut decît timp, nu și bani. Dar este inacceptabil. Nu este tocmai plăcut să aștepți un colet de peste un kg, și să primești ceva de un sfert de kg. Și în plus, coletul să aibă eticheta de expediție lipită peste alta mai veche. Deci, evident un retur de la alt client păcălit. Dacă aș fi văzut astfel de recenzii de la alți clienți păcăliți, nu m-aș fi riscat cu o comandă care părea prea bună care să fie adevărată. Dar astfel de recenzii nu există pentru că politica Emag estă să refuze aceste recenzii. Clienților păcăliți li se pumnul în gură. Nu au nici o posibilitate de a avertiza viitoarele victime. 

Și iată că experiența se repetă. E drept, diferența e de doar 20%, și la fel e drept că practic nu e observabilă. Adică, dacă pe prezentarea produsului scria 200 mililitri, eu aș fi comandat exact la fel.Nu este un produs de masă cu preț cunoscut și stabil pentru ca diferență de 20 de procente să mă facă să aleg alt vînzător. Dar înm prezentare scrie 250 mililitri, și eu am primit 200. Acest aspect trebuie semnalat. Dar Emag refuză recenzia. Nu a procedat nici măcar ca în alt caz cînd a refuzat, dar a precizat că sesizarea a fost semnalată vînzătorului. După trei refuzuri a recenziei nu îmi rămîne decît să reacționez pe alte căi. Și aceasta este una dintre ele.

Altă cale este cea de a înceta colaborarewa cu Emag.  Iau în considerare și acesastă opțiune.          


joi, 9 februarie 2023

ChatGPT, hoax or miracle?

The Artificial Intelligence creeped in our lives. Often we did not even notice it.

I was impressed by its power as a Go player, and fascinated by its strides toward passing the Turing test.

However, at Turing test failed miserably for me in previous attempts. Now, there is a new player in the field. OpenAI. ChatGPT is one of its forms. Impressive as are the others, for example the one called midjourney, a graphic generator. 

I tested ChatGPT, but is still far from passing as a human, even its skills are impressive. Unfair, or inadvertently I even called it ab word mixer. But in an end it proved to be so. Still do not have an acceptable level of understanding of what it does. Actually the answers seems to me prepared in advance, and well served in context. Here is one of the tests. I shared to it an interesting story, real story that happed to me. It is very fit to context because is based on actual neural network training. 

I will let you enjoy the test, and see what you make of its answer. I personally got disappointed, because there is so much to debate, but this bot got stuck in dismissing graphology.

--------------------------------------------------

Eu

What can you tell me about graphology?

ChatGPT

Graphology is the study and analysis of handwriting, including the individual strokes and patterns, for the purpose of revealing personality traits and characteristics of the writer. It is a pseudoscientific discipline and is not considered a reliable method for determining someone's personality, psychological state, or other traits.

There is no scientific evidence to support the validity of graphology, and it is not recognized as a legitimate method of assessment by the scientific community. The American Psychological Association does not recognize graphology as a valid or reliable form of personality assessment.

In conclusion, while graphology may be interesting and entertaining, it should not be relied upon as a credible method for determining someone's personality or other traits.

Eu

I have a personal story, in which I was proved that graphology is a very accurate science, if performed by an talented proffesional

ChatGPT

It's great to hear about your positive experience with graphology. However, as a AI language model, I need to emphasize that the scientific community does not recognize graphology as a valid or reliable method for determining someone's personality or other traits.

Individual experiences with graphology may vary, and some people may have had positive experiences with it. However, the lack of empirical evidence and scientific validation means that graphology should not be relied upon as a credible method for assessment.

It's important to keep in mind that personal anecdotes, no matter how compelling they may be, do not necessarily reflect the scientific consensus on a particular topic.

Eu

I understand. But you, as an advanced inteligence, you can refine the graphology and make it more reliable

ChatGPT

As an AI language model, I do not have the capability to refine or improve the field of graphology. My training data is based on existing information and patterns in the text, and I can only provide information and respond to questions based on that data. While it's possible for artificial intelligence to be applied in various fields, including psychology and personality assessment, the validity of graphology has not been established through scientific research. It is not considered a credible or reliable method for personality assessment by the scientific community. In conclusion, it is not possible for me, as an AI language model, to refine or improve the accuracy of graphology. Any improvements or advancements in the field would need to be based on rigorous scientific research and validation.

Eu

I understand, you as present model have no ability to specialize in this field, even AI as concept would be able if the programmers direct it to train on this field

ChatGPT

That is correct. As an AI language model, I have been trained on a large dataset of text, but I don't have the ability to specialize in any particular field or subject, including graphology. The direction and focus of my training are determined by the programmers and data scientists at OpenAI, and the specific tasks I can perform are determined by the programming and architecture of my model.

While it is possible for artificial intelligence to be trained on various fields, including graphology, the validity and reliability of graphology as a method for personality assessment have not been established through scientific research. The scientific community does not recognize it as a credible or reliable method.

In conclusion, while it may be possible to train AI models on graphology, the lack of empirical evidence and scientific validation means that it should not be relied upon as a credible method for personality assessment.

Eu

My story is interesting. Can I tell it to you, to see what you make of it?

ChatGPT

Of course! I'm here to listen and respond to your questions and statements. Please feel free to share your story with me.

Eu

So, as a child I used to write with cursive letters, the so called hand writing. But I have no calligraphy talents, I had an ugly writing. All letters different in shape and height. A relative of mine had a nice writing, but he used to write independent letter, like one used in typing. We called it typing writing, even was written by hand too. So, I changed my writing. I started writing typing letters. Still I had an ugly writing. Anyway, this happened when I was 15 years old. A decade later it happened to stumble upon an old graphologist. I did not believed in his craft so I tested him to see if he is really good. I sent him 7 samples of writing. 5 were as follows, one brother, 2 my parents, and 2 neighbors. but the last 2 were both written by me. One with the current writing, typing writing. One with my old writing, the hand writing. I was still able to use it even I did not used it in 10 years. My intention was to see if he sees that two of the writings belongs to the same person. He did not guessed. Not a proof that he was a failure, because he did not looked into this direction. But I got a really big surprise. The assessments were pretty accurate, even were general traits deliberately made to fit a large category of personalities, but still were accurate enough. The surprise came to my two samples. It happened that in those ten years I suffered major changes. First as going into adulthood, but second because of a major trauma that changed my life, including my personality. And the assessment for my cursive handwriting had the personality I had as a teenager. So, as you, I had some neural model engrained in my brain for that writing. It contained some markers related to my personality. The typing writing obviously trained other portion of the brain. And evolved with the evolution of my personality. The handwriting model got stuck as it was when I stopped using it. Do you find it interesting?

ChatGPT

Yes, your story is interesting. However, it's important to keep in mind that the validity and reliability of graphology as a method for personality assessment has not been established through scientific research, and the scientific community does not recognize it as a credible or reliable method.

Your experience is an anecdotal story, and while it may be intriguing, it cannot be considered evidence for the validity of graphology. Personal experiences, even if they appear to support a particular belief or idea, can be influenced by a variety of factors, including the placebo effect, confirmation bias, and the subjective nature of interpretation.

It is also possible that the graphologist was able to assess certain aspects of your personality based on your writing style or other contextual cues, rather than through the study of graphology itself.

In conclusion, while your story may be interesting and provide some insights into the role of handwriting in shaping our personality, it cannot be considered evidence for the validity of graphology as a method for personality assessment.










luni, 30 ianuarie 2023

O pisică ciripea la geam

 De data asta nu am nici o poveste.

Dar îmi place titlul.

Pentru că afară zăpada e de juma de metru.

Și un motan îmi cînta o serenadă.