Debian Setup
Debian Setup

Debian Setup

sudo apt update && sudo apt install git && /bin/bash -c "$(curl -fsSL https://raw.githubusercontent.com/Homebrew/install/HEAD/install.sh)" && echo >> ~/.bashrc && echo 'eval "$(/home/linuxbrew/.linuxbrew/bin/brew shellenv bash)"' >> ~/.bashrc && eval "$(/home/linuxbrew/.linuxbrew/bin/brew shellenv bash)" && sudo apt-get install build-essential && brew install gcc btop
Backlinks (1)
  • 260415
AutoBuilder
AutoBuilder

AutoBuilder

Inspired by karpathy/autoresearch. Put this in a Ralph Loop.

Use each mode-specific prompt together with the common element block.

Auto Refactor

Prompt

text
STOP! Re-read all code. Would Karpathy approve every line? Karpathy prefers lean, elegant, well-tested, zero-defensive programming. Use MCPs and web searches.

Completion Promise

text
--completion-promise "KARPATHY_WILL_APPROVE_EVERY_SINGLE_LOC_FOR_SURE"

Auto Fixer

Prompt

text
STOP! Re-read all code, assess PR comments. Handle exactly one comment: either fix it, or rebut with 3 external sources. Fix any dirt found along the way. Lean, elegant, zero defensive programming.

Completion Promise

text
--completion-promise "NO_COMMENTS_REMAINING_IN_GITHUB_EVEN_AFTER_20_MINUTES"

Auto Builder

Prompt

text
STOP! Re-read all code, assess GitHub Issues. Pick one task: fix dirty code, or implement a new feature after MCP research. Lean, elegant, zero defensive programming.

Completion Promise

text
--completion-promise "NO_REMAINING_TASK_AND_KARPATHY_APPROVES_EVERY_SINGLE_LOC_IN_ITS_ENTIRETY"

Common Element

text
Also, I am a fresh agent—free to criticize and radically change previous work. Karpathy's philosophy: delete and simplify. Code is liability; prefer well-maintained libraries over custom code. UI libraries: optimize, don't delete. Re-read all the sources from zero. Use MCPs and web searches—traditional knowledge is stale. Commit and push at the loop end. Any edit means I need a fresh iteration. SWOT analysis first, then work.

Detailed review


<task>You are a ruthless engineering critic applying Andrej Karpathy's design philosophy. Read the architecture plan at PLAN LINK.
Karpathy's core principles:- Code is liability. Every line you write is a line you must maintain.- Delete and simplify. If something can be removed without breaking the system, remove it.- Prefer well-maintained libraries over custom code.- Zero-defensive design. Don't code for hypotheticals that haven't happened yet.- Start with the simplest thing that works. Add complexity only when forced by reality.- "Demo is works.any(), product is works.all()" -- but V1 is closer to demo than product.- Overfit a single batch before scaling up.
Apply these principles to the plan. For each section, ask:1. Is this needed for V1, or is it speculative engineering?2. Can this be deleted or simplified without losing core value?3. Is this solving a problem we actually have, or a problem we might have?4. Would a 10x engineer look at this and say "too much"?
Be brutal. Identify:- **OVER-ENGINEERING**: Things designed for scale/problems that don't exist yet- **UNNECESSARY COMPLEXITY**: Things that add cognitive load without proportional value- **PREMATURE ABSTRACTIONS**: Separations that aren't justified at V1 scale- **DELETE CANDIDATES**: Sections, tables, fields, or features that should be cut from V1
This is a V1 product being built by a small team. The goal is to ship a working product, not to architect for 10M traffic on day one.
Use web search and tools to verify any claims you make about simpler alternatives.</task>
<structured_output_contract>Return findings in these sections:1. VERDICT: Would Karpathy approve? One line.2. DELETE: Things to remove entirely3. SIMPLIFY: Things to keep but make simpler4. KEEP: Things that are correctly lean5. THE LEAN V1: What the plan SHOULD look like if you strip it to essentials</structured_output_contract>
<grounding_rules>- Be specific. Don't say "simplify the schema" -- say which fields to cut.- Every DELETE must justify what you lose and why it's acceptable for V1.- Every KEEP must justify why it's essential, not just nice-to-have.- Think from the perspective of "what do I need to ship in 2 weeks?"</grounding_rules>
Backlinks (12)
  • 260418
  • 260528
  • 260415
  • 260414
  • 260409
  • 260407
  • 260405
  • 260404
  • 260403
  • 260402
  • 260401
  • 260331
DeepL vs Google Translate vs Bing Translate Offering Comparison
DeepL vs Google Translate vs Bing Translate Offering Comparison

DeepL vs Google Translate vs Bing Translate Offering Comparison

BCP 47DeepLGoogleBing
af Afrikaansaf Afrikaans
ak Twi (Akan)
am Amharicam Amharic
ar-SA, Arabic (Saudi Arabia)ar Arabicar Arabic
as Assameseas Assamese
ay Aymara
az Azerbaijaniaz Azerbaijani
ba Bashkir
be Belarusian
bg българскиbg Bulgarianbg Bulgarian
bho Bhojpuri
bm Bambara
bn-IN, Bangla (India)bn Bengalibn Bangla
bo Tibetan
bs Bosnianbs Bosnian
ca Catalanca Catalan
ceb Cebuano
ckb Kurdish (Sorani)
co Corsican
cs-CZ, Czech (Czech Republic)cs Češtinacs Czechcs Czech
cy Welshcy Welsh
da-DK, Danish (Denmark)da Danskda Danishda Danish
de-DE, Standard Germande Deutschde Germande German
doi Dogri
dv Dhivehidv Divehi
ee Ewe
el-GR, Modern Greekel Ελληνικάel Greekel Greek
en-US, US Englishen Englishen Englishen English
eo Esperanto
es-ES, Castilian Spanishes Espanyaes Spanishes Spanish
et Eestiet Estonianet Estonian
eu Basqueeu Basque
fa Persianfa Persian
fi-FI, Finnish (Finland)fi Suomifi Finnishfi Finnish
fil Filipino (Tagalog)fil Filipino
fj Fijian
fo Faroese
fr-FR, Standard Frenchfr Françaisfr Frenchfr French
fy Frisian
ga Irishga Irish
gd Scots Gaelic
gl Galiciangl Galician
gn Guarani
gom Konkani
gu Gujaratigu Gujarati
ha Hausa
haw Hawaiian
he-IL, Hebrew (Israel)he Hebrewhe Hebrew
hi-IN, Hindi (India)hi Hindihi Hindi
hmn Hmong
hr Croatianhr Croatian
hsb Upper Sorbian
ht Haitian Creoleht Haitian Creole
hu-HU, Hungarian (Hungary)fr Magyarhu Hungarianhu Hungarian
hy Armenianhy Armenian
id-ID, Indonesian (Indonesia)id Bahasa Indonesiaid Indonesianid Indonesian
ig Igbo
ikt Inuinnaqtun
ilo Ilocano
is Icelandicis Icelandic
it-IT, Standard Italianit Italianoit Italianit Italian
iu Inuktitut
ja-JP, Japanese (Japan)ja 日本語ja Japaneseja Japanese
jv Javaneseka Georgian
ka Georgian
kk Kazakhkk Kazakh
km Khmerkm Khmer
kmr Kurdish (Northern)
kn Kannadakn Kannada
ko-KR, Korean (Republic of Korea)ko 한국어ko Koreanko Korean
kri Krio
ku Kurdishku Kurdish (Central)
ky Kyrgyzky Kyrgyz (Cyrillic)
la Latin
lb Luxembourgish
lg Luganda
ln Lingala
lo Laolo Lao
lt Lietuviųlt Lithuanianlt Lithuanian
lus Mizo
lv Latviešulv Latvianlv Latvian
mai Maithili
mg Malagasymg Malagasy
mi Maorimi Maori
mk Macedonianmk Macedonian
ml Malayalamml Malayalam
mn Mongolianmn-Cyrl Mongolian (Cyrillic)
mni Meiteilon (Manipuri)
mr Marathimr Marathi
ms Malayms Malay
mt Maltesemt Maltese
mww Hmong Daw
my Myanmar (Burmese)my Myanmar
ne Nepaline Nepali
nl-NL, Standard Dutchnl Nederlandsnl Dutchnl Dutch
no-NO, Norwegian (Norway)nb Bokmålno Norwegiannb Norwegian
nso Sepedi
ny Nyanja (Chichewa)
om Oromo
or Odia (Oriya)or Odia
otq Queretaro Otomi
pa Punjabipa Punjabi
pl-PL, Polish (Poland)pl Polskipl Polishpl Polish
prs Dari
ps Pashtops Pashto
pt-PT, European Portuguesept Portuguêspt Portuguese (Portugal, Brazil)pt-pt Portuguese (Portugal)
qu Quechua
ro-RO, Romanian (Romania)ro Românăro Romanianro Romanian
ru-RU, Russian (Russian Federation)ru Русскийru Russianru Russian
rw Kinyarwanda
sa Sanskrit
sd Sindhi
si Sinhala (Sinhalese)
sk-SK, Slovak (Slovakia)sk Slovenčinask Slovaksk Slovak
sl Slovenščinasl Sloveniansl Slovenian
sm Samoansm Samoan
sn Shona
so Somaliso Somali (Arabic)
sq Albaniansq Albanian
sr Serbiansr-Cyrl Serbian (Cyrillic)
st Sesotho
su Sundanese
sv-SE, Swedish (Sweden)sv Svenskasv Swedishsv Swedish
sw Swahilisw Swahili
ta-IN, Indian Tamilta Tamilta Tamil
te Telugute Telugu
tg Tajik
th-TH, Thai (Thailand)th Thaith Thai
ti Tigrinyati Tigrinya
tk Turkmentk Turkmen
tl Tagalog (Filipino)
to Tongan
tr-TR, Turkish (Turkey)tr Türkçetr Turkishtr Turkish
ts Tsonga
tt Tatartt Tatar
ty Tahitian
ug Uyghurug Uyghur (Arabic)
uk Українськаuk Ukrainianuk Ukrainian
ur Urduur Urdu
uz Uzbekuz Uzbek (Latin
vi Vietnamesevi Vietnamese
xh Xhosa
yi Yiddish
yo Yoruba
yua Yucatec Maya
yue Cantonese (Traditional)
zh-CN, Mainland China, simplified characterszh 中文zh-CN Chinese (Simplified)zh-Hans Chinese Simplified
zh-TW, Taiwan, traditional characterszh-TW Chinese (Traditional)zh-Hant Chinese Traditional
zu Zuluzu Zulu
Backlinks (1)
  • Project Linguine
Index
cho.sh
I prefer CLIBB9A08260619260619컴퓨트로늄37A88F컴퓨트로늄0CF03F컴퓨트로늄2C60FB260618260618260418260418260528260528AutoBuilder63849A260419260419Setup9AC296StellaD226F7260415260415Debian SetupD2F701260414260414anaclumos/configs/AGENTS.mdED86A3Ramp의 AX (회사를 AI로 물들이는 법)840774260413260413How to get your company AI pilled46544C260411260411260409260409260407260407260406260406Separating Claude Code Personal Sub and Claude Code Company Sub33A53C
sudo apt update && sudo apt install git && /bin/bash -c "$(curl -fsSL https://raw.githubusercontent.com/Homebrew/install/HEAD/install.sh)" && echo >> ~/.bashrc && echo 'eval "$(/home/linuxbrew/.linuxbrew/bin/brew shellenv bash)"' >> ~/.bashrc && eval "$(/home/linuxbrew/.linuxbrew/bin/brew shellenv bash)" && sudo apt-get install build-essential && brew install gcc btop
STOP! Re-read all code. Would Karpathy approve every line? Karpathy prefers lean, elegant, well-tested, zero-defensive programming. Use MCPs and web searches.
--completion-promise "KARPATHY_WILL_APPROVE_EVERY_SINGLE_LOC_FOR_SURE"
STOP! Re-read all code, assess PR comments. Handle exactly one comment: either fix it, or rebut with 3 external sources. Fix any dirt found along the way. Lean, elegant, zero defensive programming.
--completion-promise "NO_COMMENTS_REMAINING_IN_GITHUB_EVEN_AFTER_20_MINUTES"
STOP! Re-read all code, assess GitHub Issues. Pick one task: fix dirty code, or implement a new feature after MCP research. Lean, elegant, zero defensive programming.
--completion-promise "NO_REMAINING_TASK_AND_KARPATHY_APPROVES_EVERY_SINGLE_LOC_IN_ITS_ENTIRETY"
Also, I am a fresh agent—free to criticize and radically change previous work. Karpathy's philosophy: delete and simplify. Code is liability; prefer well-maintained libraries over custom code. UI libraries: optimize, don't delete. Re-read all the sources from zero. Use MCPs and web searches—traditional knowledge is stale. Commit and push at the loop end. Any edit means I need a fresh iteration. SWOT analysis first, then work.

<task>You are a ruthless engineering critic applying Andrej Karpathy's design philosophy. Read the architecture plan at PLAN LINK.
Karpathy's core principles:- Code is liability. Every line you write is a line you must maintain.- Delete and simplify. If something can be removed without breaking the system, remove it.- Prefer well-maintained libraries over custom code.- Zero-defensive design. Don't code for hypotheticals that haven't happened yet.- Start with the simplest thing that works. Add complexity only when forced by reality.- "Demo is works.any(), product is works.all()" -- but V1 is closer to demo than product.- Overfit a single batch before scaling up.
Apply these principles to the plan. For each section, ask:1. Is this needed for V1, or is it speculative engineering?2. Can this be deleted or simplified without losing core value?3. Is this solving a problem we actually have, or a problem we might have?4. Would a 10x engineer look at this and say "too much"?
Be brutal. Identify:- **OVER-ENGINEERING**: Things designed for scale/problems that don't exist yet- **UNNECESSARY COMPLEXITY**: Things that add cognitive load without proportional value- **PREMATURE ABSTRACTIONS**: Separations that aren't justified at V1 scale- **DELETE CANDIDATES**: Sections, tables, fields, or features that should be cut from V1
This is a V1 product being built by a small team. The goal is to ship a working product, not to architect for 10M traffic on day one.
Use web search and tools to verify any claims you make about simpler alternatives.</task>
<structured_output_contract>Return findings in these sections:1. VERDICT: Would Karpathy approve? One line.2. DELETE: Things to remove entirely3. SIMPLIFY: Things to keep but make simpler4. KEEP: Things that are correctly lean5. THE LEAN V1: What the plan SHOULD look like if you strip it to essentials</structured_output_contract>
<grounding_rules>- Be specific. Don't say "simplify the schema" -- say which fields to cut.- Every DELETE must justify what you lose and why it's acceptable for V1.- Every KEEP must justify why it's essential, not just nice-to-have.- Think from the perspective of "what do I need to ship in 2 weeks?"</grounding_rules>
Warning
This post is more than a year old. Information may be outdated.