I'm trying to crack a crypt with a known key length. I deduced that the operation made was a hex XOR. Here is the crypt:
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
I have tried to use this tool to decrypt it. The tool outputted multiple possible keys and for each key, an attempt do decipher the crypt. I know the result should be plain text English. The closest I got was this:
T-e po1ato ,s a 6tarc-y, t0bero0s cr*p fr*m th per nnia) nig-tsha!e So)anumetube7osumeL. T-e wo7d po1ato (ay r fer 1o th pla+t it6elf ,n ad!itio+ to 1he e!ibleetube7. Inethe ndesi whe7e th spe&ies ,s in!igen*us, 1hereeare 6ome *thereclos ly r late! cul1ivat d po1ato 6peci s.P*tato s we7e in1rodu&ed o0tsid theeAnde6 reg,on f*ur c ntur,es a"o,a+d ha3e be&ome $n in1egra) par1 of (uch *f th wor)d's #ood 6uppl<. Iteis t-e wo7ld'sefour1h-la7gestefoodecropi fol)owin" mai?e, w-eat $nd r,ce.
After some digging and manually tweaking the text, I got this:
The potato is a starchy, tuberous crop from the perennial nightshade Solanum tuberosum L. The word "potato" may refer to the plant, itself, in addition to the edible tuber. In the Andes, where the species is indigenous, there are some other closely related cultivated potato species. Potatoes were introduced outside the Andes region four centuries ago, and have become an integral part of much of the world's food supply. It is the world's fourth-largest food crop, following maize, wheat and rice.
It unfortunately did not work. I am now trying to find a clue as to what I should be doing to find the answer.
Related
I registered at this link to get an API for ChatGPT.
And I used the chatgpt package in R.
library(chatgpt)
And set environment:
Sys.setenv(OPENAI_API_KEY = "sk-YOURAPI")
I used this function:
chatgpt::ask_chatgpt("How to make a strawberry pie to donate to my wife? Ingredients, please.")
Sometimes the output is missing words. For example:
*** ChatGPT input:
How to make a strawberry pie to donate to my wife? Ingredients, please.
[1] ... and your wife is"
It does not complete the text after is. Is there any solution for this on R?
Similar question on reddit.
EDIT
I tried increasing the processing time of the function (so that the chat would finish typing all the content, without stopping midway). Like this:
for (i in 35) {
print(chatgpt::ask_chatgpt("How to make a strawberry pie to donate to my wife? Ingredients, please."))
Sys.sleep(i)
}
What you are running into is prompt engineering. GPT is a sophisticated autocomplete engine.
If you are not getting the right response you need to recraft your prompt.
You can always test your prompts in the OpenAI playground:
https://platform.openai.com/playground
I was able to get a list of ingredients and cooking steps by using the following prompt:
How can I make a strawberry pie to donate to my wife? Please provide first a numbered list of ingredients, and secondly a numbered lists of steps.
Here is the output I got in the playground:
Ingredients:
1. 2 ½ cups of fresh or frozen strawberries
2. 1 9-inch pre-made pie crust
3. ¾ cup of granulated sugar
4. 2 tablespoons of cornstarch
5. ¼ teaspoon of salt
6. 1 tablespoon of fresh lemon juice
Steps:
1. Preheat oven to 425 degrees F.
2. Place the pre-made pie crust in a 9-inch pie dish and set aside.
3. In a medium bowl, combine the strawberries, sugar, cornstarch, salt, and lemon juice. Stir until the mixture is combined.
4. Pour the strawberry mixture into the pre-made pie crust.
5. Place the pie dish on a baking sheet and bake for 15 minutes.
6. Reduce the oven temperature to 375 degrees F and bake for an additional 25 minutes.
7. Allow the pie to cool completely before serving.
Another thing to note, per the Github repo for the chatgpt R library it says "The {chatgpt} R package provides a set of features to assist in R coding."
Ref: https://github.com/jcrodriguez1989/chatgpt
I would use the OpenAI APIs directly, this way you will have a lot more control over your response. I am not an R specialist, but this is how the OpenAI Playground showed me how to do it.
library(httr)
response <- GET("https://api.openai.com/v1/completions",
query = list(
prompt = "How can I make a strawberry pie to donate to my wife? Please provide first a numbered list of ingredients, and secondly a numbered lists of steps.",
max_tokens = 200,
model = 'text-davinci-003'
),
add_headers(Authorization = "bearer YOUR_OPENAI_API_KEY")
)
content(response)
Ref: OpenAI playground
Increase max_tokens to get longer answer.
This question already has an answer here:
avoid string printed to console getting truncated (in RStudio)
(1 answer)
Closed 6 years ago.
As a beginner, I am currently working with web scraping with R, using the 'rvest' package. My goal is to get the lyrics of any song from 'www.musixmatch.com'. This is my attempt:
library(rvest)
url <- "https://www.musixmatch.com/lyrics/Red-Hot-Chili-Peppers/Can-t-Stop"
musixmatch <- read_html(url)
lyrics <- musixmatch%>%html_nodes(".mxm-lyrics__content")%>%html_text()
This code creates a vector 'lyrics' with 2 rows, containing the lyrics:
[1] "Can't stop addicted to the shindig\nChop top he says I'm gonna win big\nChoose not a life of imitation"
[2] "Distant cousin to the reservation\n\nDefunkt the pistol that you pay for\nThis punk the feeling that you stay for\nIn time I want to be your best friend\nEastside love is living on the Westend\n\nKnock out but boy you better come to\nDon't die you know the truth is some do\nGo write your message on the pavement\nBurn so bright I wonder what the wave meant\n\nWhite heat is screaming in the jungle\nComplete the motion if you stumble\nGo ask the dust for any answers\nCome back strong with 50 belly dancers\n\nThe world I love\nThe tears I drop\nTo be part of\nThe wave can't stop\nEver wonder if it's all for you\nThe world I love\nThe trains I hop\nTo be part of\nThe wave can't stop\n\nCome and tell me when it's time to\n\nSweetheart is bleeding in the snow cone\nSo smart she's leading me to ozone\nMusic the great communicator\nUse two sticks to make it in the nature\nI'll get you into penetration\nThe gender of a generation\nThe birth of every other nation\nWorth your weight the gold ... <truncated>
The problem is that the 2nd row gets truncated at some point. From what I know about rvest, there is no parameter to adjust truncation. Also, I could not find anything on the internet about this issue. Does anybody know how to adjust/ disable truncation for this feature? Thanks a lot in advance!
Best regards,
Jan
I think its better to copy and paste the lyrics into your Notepad or Wordpad. Save as a .txt file
Then use the readLines function, it prints our a warning message but I was able to have the entire lyrics in 84x1 chacacter vector which you can clean or do whatever you please.
words <- readLines("redhot.txt")
> head(words)
[1] "Can't stop addicted to the shindig"
[2] "Chop top he says I'm gonna win big"
[3] "Choose not a life of imitation"
[4] "Distant cousin to the reservation"
[5] "Defunkt the pistol that you pay for"
[6] "This punk the feeling that you stay for"
No truncation problem here.
If I begin with a wholly Japanese sentence and run it through MeCab, I get something like this:
$ echo "吾輩は猫である" | mecab
吾輩 名詞,代名詞,一般,*,*,*,吾輩,ワガハイ,ワガハイ
は 助詞,係助詞,*,*,*,*,は,ハ,ワ
猫 名詞,一般,*,*,*,*,猫,ネコ,ネコ
で 助動詞,*,*,*,特殊・ダ,連用形,だ,デ,デ
ある 助動詞,*,*,*,五段・ラ行アル,基本形,ある,アル,アル
EOS
If I smash together everything I get from the last column, I get "ワガハイワネコデアル", which I can then feed into a speech synthesis program and get output. Said program, however, doesn't handle English words.
I throw English into MeCab, it manages to tokenise it (probably naively at the spaces), but gives no reading:
$ echo "I am a cat" | mecab
I 名詞,固有名詞,組織,*,*,*,*
am 名詞,一般,*,*,*,*,*
a 名詞,一般,*,*,*,*,*
cat 名詞,固有名詞,組織,*,*,*,*
EOS
I want to get readings for these as well, even if they're not perfect, so that I can get something along the lines of "アイアムアキャット".
I have already scoured the web for solutions and whereas I do find a bunch of web sites which have transliteration that appears to be adequate, I can't find any way to do it in my own code. In a couple of cases, I emailed the site authors and got no response yet after waiting for a few weeks. (Just how far behind on their inboxes are these people?)
There are a number of directions I can go but I hit dead ends on all of them so far, so this is my compound question:
MeCab takes custom dictionaries. Is there a custom dictionary which fills in the English knowledge somewhat?
Is there some other library or tool that can take English and spit out Katakana?
Is there some library or tool that can take IPA (International Phonetic Alphabet) and spit out Katakana? (I know how to get from English to IPA.)
As an aside, I find that the software "VOICEROID" can speak English text (poorly, but adequately for my purposes). This software uses MeCab too (or at least its DLL and dictionary files are included in the install.) It also uses another library, Cabocha, which as far as I can tell by running it does the exact same thing as MeCab. It could be using custom dictionaries for either of these two libraries to do the job, or the code to do it could be in the proprietary AITalk library they are using. More research is needed and I haven't figured out how to run either tool against their dictionaries to test it out directly either.
I've been stuck by this issue for a long time. I have two networks in my model, so I want to create different types of links with different breed turtle agentsets.
Let's name the 1st turtle agentset T1 and the 2nd T2, so what I did is the following:
breed [T1s T1]
undirected-link-breed [TL1s TL1]
breed [T2s T2]
undirected-link-breed [TL2s TL2]
;;Got error report
ask T1s [create-TL1s-with other n-of 10 T1s]
The last line gave an error reporting that "You cannot use breeded and unbreeded links in the same world". I'm quite confused about what this means.
And then, I changed the last line to:
ask T1s [create-links-with other n-of 10 T1s]
It worked this time, but if that's the case, how can I define two different types of links, i.e., TL1 and TL2, with different turtle agentsets T1s and T2s?
Can anybody help me out? I really appreciate it!
Thanks
That error means that you've created some links that have no breed (probably with create-link-with) before creating links with a breed, or vice-versa. If you want to use link breeds, you can never use create-link-with, create-link-to, or create-link-from. You must always use create-<breed>-with, create-<breed>-to, and create-<breed>-from.
So, search your code for instances of create-link-with, create-link-to, or create-link-from and either delete them or change them to create-<breed>-with, create-<breed>-to, or create-<breed>-from. If you're still getting the error, call clear-all or clear-links to make sure you've removed all unbreeded links.
I developed a new method of encrypting information. It does not comply with standard methods of encryption and was custom made to encrypt info stored in session cookies.
It basically works like this:
-It takes a standard 72 char string as it's IDENTITY or password. There could be more than a million variations of this.
It then uses a pre-defined set of randomly generated variations of text and uses that to hide the actual content. However, it has special chars hidden in each enrypted line to help identify how to decrypt it.
My reason for posting here is to see if anyone here could (a) crack it or (b) give me some advice on how to make it better.
I am not too reluctant to give too much info yet as this is still in aplha stage and not the finished project.
Here is an example. It is the 50 US states in random order. Please note that even if I keep the same order, each time it will look different. To prove that, I will run it twice with the same order used:
First Run:
H39pwxMnczu+#u!?:IeQAAeSPrjJFRZ84#zma-XbMaU7#F|Bm!6o3qgnJ3 cFIoTYNS|dAfVa
ibes!zd!O-e4sxx8yOo!?hTvK-f6htqlRxT?pV3CT--l4vU#7TInYV-WXNFil-t3+tG+:9b5X
?9#2Ncfn8AUim!3LZw#s5YRqF5Xfwm1:sCO?B90ViBQkmW?MlHn1h4Pd5AU8Lw QYwzr8IxhB
0r!mccmccmffmRzbapQ_dSjm+9#5jRR_IlqvWjY:Z9RfiABL_Rp#Dp!DyP?HiAB#9+HXRp?1x
SHjCpl+lvLvKVECH#bY+jn?T_-:1T7M#x?4uQ!bsJglVmc5dHN79HUF58|sTVDIp#jN__8tIk
?5ErfVd2N9TgcR3pWE#Dw98FYnUT9BHlBolV:mPFYnHw5P69BmJhWo|fYYL25P?rguINWY+f4
P?6QBXUxyYg3iWNpVL2FoBd-s UaqyAaOc M#2xd6ewglq??MZe4nD-#UnW3H6Fa?TIAdegkd
ERM?yyKtW_IydIOm77ia:9ao8 o#RcB8u_G3Jwox-K?0IC#S22GG0wQH-hfbptWSCCKo0Noaj
SRnCpwIzQv2CwvtH_Qt2RUT9ms#TDY9#Jb9J88m_V5xmQL_Gnj_9kO5JiRYVN0pY?YW_RnI9g
rDVUGkUuEg76dDXVawq|SImE8MyKKDDmar+|vHh93?y88SwmFwtYvzCNEA52n:eCfu1PGgH k
RO6ZAV7VO3S:3WWz+1LGzlb+o#!+:xyL3BKA1jIHArAd+K#4:5k2 Oi2Og2F|:DI+fxXL|f7G
DmqBiMZv2277kCjE# 6JPAorUURxk+xNB p?ew!cnuTz?GMqO8v63tJ7Mu TGoENfSN6Q4C7Y
!VMBYFY5YLadz0!TnjMrVA8Sr2rFdML-zR45:9m59i5e zg8dx0+T x?1LP79cFTnj:mc93w
S#?vL+v+i+mNXmV:W4ckvwjGMJRcQKAntLxgIH9KMWJQFTVb!Vxhlp9ELJ_7FVBU2YD:gJbAL
omUd_SFpmR_dXC RwigvHF67DObZdOZ-O_f6#egP4lMfP?BHzJZEiMj!bdEZQSfTsRBbWrzm:
09!mIINcG-n??B1-jQfdA#_lp|tG++M9jpedAJ_mpzd+P 7Ws5MD4Y#+p4dP97n0?HYR4!0Z+
cEtiKjA:6hfp+#D2ClS-2eH9e1dDsNZ7mN5vwR- a:EZ6j|3Py#I3ivk0hfp1|KIglp-Jz-d
|c9O:#Ue5Mk575P004EY 9QKC!5 cQ0ysIGgp46Z-r0 ZQyEIPLVo-HZXLN0RRiYbAYV0S_ZV
xXY#8SAwW ZB?Sr4OcL!ncpl+#m_W?iL5HAJ3 Z0Jol9|DyC-A80UgCm7zmr_8QMOpDmHE4XF
:r7:LlgSvzJuKm6oXy8r#XRMaJvNsnydX?N-rtt4Y73YsrwIXsf6nKoYf7Zc be:dj0ppKKh#
G-f8w8PPb-Z-oHp:BPAVDj-MHvSZyp0_E8k mwZvLLp?30AaFCUO!DUZ+h:#OS637Am6UXKUu
TcWQAUyQ:VJKv94zus2X9tn88p3vD34tgr2iupAwD+INKoMQuc?mXeZoouyKDohTm6 JoveXP
dP27Gb4iLdZ51w7YDr8#XTdisjQGrYII#BnX6P532?KH2r0LtS?D:nN6Q:2-_2lGDcZU3THX3
wAt9|j:9:OyvSwM8GmuFAN0zbg:eGXTUaknggG!bAgcqU62PgrkaxGCTXCtGlrF|lGq:XdUT1
np1lj08kyIC-qNcOpxAwjxS9Y|#A6g-dNJgxiDx+K6W?vp3jqpplpSDvTI:49N|16NHZNs :i
qA_92j6!YML9jMMF mv|b5NSS K97Seq|8JXS+5b2 zvmzf c+BCc qMmr|vyhVgc+xLhn_Oh
3O!9IS|9Vj9BY_G J-0: !zf!ZIGLjuq|Reqq9q4fuPt8vm0y5G0#H0p78zeYE6eGd3O sO+5
4KxCIUCRCe614E_K 5aI72VD297P BMP76eD|1VqjmRP uXjdF3jP|NiCBPoVUKmx1QT_skiB
rD_IvYESiE::6th4CKM67?:hNStD1:g _xH_jdY54#+y8YK+snh2|zyf0:we UtwCKHhcI:jc
j4vbZ0hkYSkr2!Vq5ua+rxT4mHUxGtLYEEXXxeTAmzsyG_vL4hX:xeArSKJq8ldm4ij2qklrx
848Tf?I76s?TZVDsSW7NW M6om3j+E6|jiIbOR_+5uD4US?14G|Nb9dD 961hLBj1zsb!0bZo
QefvLrM!sP:OmqqRRsHuCNV_BPG0O83RXsHCapIbJ75#N8czeJx5as7LxiFv#5cVydKyrsPL3
gJxaabTzbY!7LSCNsZ-XhBFrl1dbtleLgsPmrHP7tK2VStDTs qsJ07ckxwul2mwXg_Xrr8nw
glo3YkbTQnzTQJ5evtzc8gDulM0o qF_std?h TFlgqwTrKm_Fd-74j73gJwzrK0gloYJteVS
aHDL7A+ZHlFLIygly8nkKBqQjNUQF8 sC48pgqJDq|?FV+ih-nsjh#Bw#NN1AhGL+Jm78BqAw
H-U8Jyg7n:6ei#af:qF?erI6l?As8iefonU9nwI-l7As!IrRm-ajd3F|0NVM-sccAbZIMC6VF
JqWhZczdLcpfqn_5kNwuKe30yKP6e8|ZeqXO3k8Vn3CFkDB_ke??9qDMr8tfqpRvqkGhMe2XF
AAx7JTdlXYYSdVMdA1!NjHgS1RNdUI2AxCDcaJuS8iiwm#NuxeJcNK7jSuiDA2ZAj!lj+n7D_
-FQf::fvo9:1MM:YVuA0VxX-+yuhn+61y 4vyVddlx aIupDxQFMxyPtaVcX1!mhmZAmLxT5W
CC603Xv0n:CqhLd 9:1g3yFpS2CYaaOf8L2gtSFLjWTC2ay1:v1T0kTQ?WyRNn14Qv_zy5|6l
qSU9E92MC9hstXhHAA+Ssy 5-aSKejShBLyHdfFDC:C1WCRSpOvAx8|4zwjcV|M18b:PnBqmN
pGWHgmJUU3:sBt|6lSB+2?9tUMGCXG?mk?1_2MufcGW1XdiMDY7Td3#HckI!h+Qsp?SjNB3 ?
p97lhhHvpl7#E93wDTkoWeiCtCB6Ca9lMN:rjvVugE?IvmBjht_|wUQ1|XS#Xp9_agWo2gd5R
Ua9QU!j|UQ|G:tdALda+OaP-bthr|dmPLW9tc01_WBJj|OHIU9:Qk8o:kHm3CE95BP?W6ptd3
usPh|dRWdWftqwqtZ21#4R5O4+ 4#T2C?nkCjbSZMM#Ml5YqO-?q:HL?J|sT3h-#rQ9#gB09P
j4ehkYokoQUs2Gvb5GS?xv_Tmmis?wO1TrHY1r_txSAJG+C04nza5xZ:dH93a!C0G56X4#fAx
us:1SdYdh14#T2C?nkCjbSZMM#Ml5YqO-?q:HL?J|sT3h-#rQ9#gB09P5t4QK_wb3XZiO|ZFS
p4sHcceZElZvE+Nh:gUlQqEUQIWBswi931xdjFMGBpaCqrTM#1x9GXZdRJwBBjU3IUcpG!sHG
jmQbkkb??bb9aO4Chq4HvXq_jG:iZh5Uux5VWYxwa2+uT1n#iLmKCjmf6oGlwssJE0qHP+qtd
gJ-mTnvc?VoJrCXtG-fSg78_B!wfPCXJSactZKuggGNr5NT7S0MzS1J 0QQrhDvlxH?t 3V
Second Run:
GAG58FX0vFXjbXH-S#Np6aEPC6ekzwQvpbP0 3F8AihC9UdZ0+2of_70kfqv?KH-SQo5kyEAM
hjLKSsOShgSjjH3Grh|YMjqC6fwRji hY9v?aJZDunghjC FYvd#x8nxCm#theeFMuXMrhTlC
:dZNv3gLrJMp04uYXAL 5z3v#nkrCjDa c:oPi6 pPVY?fIsduoUp7T#mb9rYCUN2AvIr:epy
p1rJJrJJrhhr4HM!mtC6AQiYq 50jSC!Gt?6QcrfEjfGorwCll?s0UsnCdhG34 EY5sj0I7F
kxATb4J4aBae!wHoXJx0WnZdLl0pdP V_s9m17E:ex5b#3ok83maad-2pXIwxUXvNUEnnyLXH
AoRZTCJ2!T#4-c::ZcokDSyFgo#9TTlncSKkMCstgolM jnvB4sibSNV!O1Xdj884jdEpwRI7
hM1S#R|RM1GKrJlMx7uChoIdYQnZYMSSem96piXhBpqGB7EE3fpxv9Zjn|BOfB#FxLVShoI6h
Dz3ivvRAodwv4wlgZZrQm73U8BLYANr8dJQ0p!Lus76Cwj#SxJII!JxDKTnktxm#j27FCTFY7
RK#iHq4tlVDiqV3Mr73+VVhWnz6f2|#6yq#gFFBU61en7OrZ#DU#_T1KIV|CHz||N|3UaQcki
qSKpX6p:MgXacPBTjDqRS1|MytVmc??jcmdLh5r6m tywS8|h8_Sh apmSLq1AMaC+9bh Yv+
QJdvgr#rdpm76yyoGd8Zb#JVv7zG7uR8-LrN!OaNNXNiGEM?53CJoI8JHUJPf5za:BWa809sZ
CFg3J2sndTYYBTdm5Oh9WdFqlDC wO NCOF|SdC5aLf0|:1sAOFpu1Rt1LOfpkbjAVNQI1Ttn
PdjcQ1QWQy-wUagFcNgxQxV#G_x6_g3bHF3m8Jjfmgmp0ZaVTAA4OeAR 3RqJTgjc??jb2?v0
xL+B? B m3gyOgBCnPy:me40_ZZyiYBCM|zl7DA00nH8v EC4ozl7hDr|H:irBmLv9rCl?DB|
jSWhZYRNSoZh6Tko5ePqx8d+x9jOwJ9q9HyXm_YGGt!RGUsxUVOYqw622w8I2#y45KkjCzS++
! vpssP#mwYBBcVoY1t:TnLqPzzv5mu#F1 QTnLxqy:5wVyYd9uKy1nsqY:wSyji79D-8diOs
XCV34ukN|9|WzyBUU0+ZU!i6!JbB:LS88L238 |CXRNP-lxppoMipVK6A9EpJx#r20jXCQkfC
u!e1W0uHKh2KRKdD-HW59Zf84MQ_CwD0qCdt?HVC94R_dw0XCl!T?:znt!rR44gLCb5|R9aft
s7RcsundeK|Y8u1xE7|gg7VUgLt2kQ8W?Pw--aO0-N!S3lq-hwizVe9k2yrI2iBEEVurPbz3k
cEXHAQK:TEdT-ZCkdpv:hT0n5d+r!ZxRb-rs:vvgNdW4l:pai-3CZfkNpdfoIDPu6Z-15aaxS
AcH!Y!JJCpCbHJOosE2NF+bc:MJSd!TAtkjoNIj2eewlovAdRTcAjFljX1SwAJdoyuNsW2wc9
Nd4brngbG+DCb+1NL1U-+BBAxDXbHX1cm1qzyWcwCXFiH1v30r4P-U3:CXXgS?dVPdM9pUU-Q
X+Qnb_IduieZkrnWkUAd4XQ?zC6Jzv22p8CgXA 4:Xz#8zylUpXkAC5|6VRvp:+JkUoF4X#iN
q7fgCpMgMH7rt7+?RCrn9HV5T7xUEw_bP1Uv9HHKgBmYbm A211PJLS_|S+Lj1ne2EYxwSW_s
ipqEg:X?!c-pYtxIgbtVG-VFMNct?xpiXTSLQcbfw?NPJgtGW4p#4zTJLZ-UFmPTvEt8mdb-Q
kuXTnNQz|asTNayvWFXJK v7TmmVBMp|Jp9un K!s0Xb0esN 5EnW|yF0UXotdAN#x+t9mtl
-Eb1J#-1|:18ylTE+ hZ!pmyIF6TxSr2lQWY+CY:Zrp8Vj-RSZo1lGRtIVmPyzdWV+?Dn4D5Z
!zupeZpspY0j?zc37puAR+LM+BRQg c34d1!8yziP94:2ntqeVJD8ynp1szKB6VXe_9gyZil5
hrp|wESsOSh6JjB8BGCBH?9:vxjxnhM1fO6naExgQCAu8RrA7Fx7iMCH16h9K|M8EsLrVY6:y
Zf#puO9hDFNPUqwJW0:SGmp2woALX-ufvV:SL8WhGt_1f ub2NScmQOPoYzJ4TlG2RcUJIhPS
_ObYH2 Jk72YU-LG1S+O-DkURITg547tg#NU#8GTe1OLyHhG4kzZt0VOnpJ1QMiVxW+aGJtcC
Fm7|tY1feJyc5ngtpeFPM6kjG54cQUzp!TNX_sv1m3:Y6UD!amHM_px mCMYp::vhNZMqex9j
VQ0qqPuIPYwuQeD2UDjGpKlrHZqXGwVY?QJWrtMIl|CdW8-RcGIQ_6u1e9hoQz#HGD1Prrn!H
WLqm:eKU2jtUkDEwAf1L2?I7xbe:gShmzfo2CgcUxL|jgqUmLhhetInURV|a_LSKVxjtDNna4
Qp73OmWkpry3wuxrveKyM-PLia5A3Hd#giIXzFe3PJqxEsTm+P2rNe6Euaa9_N0wvefCJiFCr
7:x!sRIUtHyZXI#:Gx4D97prCQ89mXZMD+?d+VesF:vPDblFyytLF6UdSI!84EBl9yIFKA4O
9F+3I6B#e65AEKQhDPrEDcbIVW9scy BcEnR?2ywFbhC2vpt2c:lf?HDudzNE0P-E2UiTnk46
GKir5CGmzJfE7FEBly6nQXfiH6PPv_6j5FsWa YK?HCPW6+dYc4#U+fK??FQVi+nyGnH1aFY
wc!:aa:PzUae88aBrc2zrAkqGXc|gOF5XwVfXr umGylJ4jxAL3TAX9+8k7e:yfPfIh:qAe10
2RIPO7LP|09zfg66O7gpSbDQ20?GEfW6Qg+B?TqUa+9GEEbrPz+RcCRfI2b?pD+rP4nNcdRj3
gJMzaz73_zlK2VlSALg qshMb7t5!UtlTQnZBm3qVcVrO3NtmwaeHA7BFJuJ2uLGezg4aXrs1
f mS+!RNg:xZ3OvGhIiLOARNN0j!8OK+ Kg620GbuOj!QDB+nKmcD0t44O|kAvBM?KIcL00TK
fK6QTTSc_QIMHA0?nU|w2!VqNq3R!hA2PExBz_w9KCKyC+ZxSOXEL3:i4 u+uDG6nKjN2KDWg
F_CF1GhM1FMvkGm4XmpGjdEZHA-xhmN4JQsgjdUVQPPx8zmU96pgRp5Vc|PidU6Jqpkf ylKs
gJ17?3TY3YHN?s5BurGPLhsVAl0AcgrHkJFKk3SdX MTYsJaVhR5wtlRmgDC? 5c8fG1US4!v
UW1j|o+|+jOHMrE68LsyYE33e4cOyS5k8xkWYnK3usy5r0kTpo:gt6yPu_55N0DdItdam+yy6
gJBma3L37mAcgrHkJFKk3SdX MTYsJaVhR5wtlRmgDC? 5c8fG1US4!vsBefg1n3ht7QlZOXS
bCYjqq#b?tbN?p FN-cyocxVu#HSLF-EncXQ?_290F3SJ--Gn5z69zAkwFF0S?Zn8Z aYzcBw
UahK||KUUKKUa5LDOTH_WkTK31PcyH!qt6Y4druSa8gt3Yo+OWnGkMw?da1LSppnBdQkWgG3k
R:rZbqHTDa:6Azhrq8Md OeBI::jAac!dc|xVOO Bq3A73+-yczUVq-fY3gnec5S7iorx|:4Y
As you can see, it looked different for the same order of 50 lines of text.
So, any ideas?
Any encryption method which relies on the secrecy of the algorithm is flawed. The attacker will always know the algorithm. See Kerckhoff's Principle for a longer explanation.
It is absurdly easy to write an algorithm that you yourself cannot break, anyone can do it. However, unless you are a professional cryptographer, a professional cryptographer will find it easy to break. Have you tested your algorithm against differential cryptanalysis? Do you even know what differential cryptanalysis is?
There are many excellent cyphers available already, suitable for many different purposes and with varying levels of complexity and security. Don't reinvent the wheel; use an existing cypher.