260415
Backlinks (0)
No backlinks found.
260415260415
AutoBuilderAutoBuilder
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>Dilemmas of Technopreneur
Dilemmas of Technopreneur
If you are in a competitive VC-funded space, it's foolish to compete without raising money. Don't bring a knife to a gun fight. Andrew Wilkinson (@awilkinson)
For 10x Technopreneurs, the Cost of Engineering is relatively cheap because they can do the initial work. Therefore, they do not need the upfront budget to collaborate with the engineers to create the first MVP. That means the First Two Months of a Startup can be spent making the product rather than focusing on the team or preparing for funding.
This can mean good and bad things for them:
On the bright side. If the technopreneurs are lean enough, it may be much more efficient to check the Product-Market Fit. Essentially, they can Cut the Fat. There are dozens of examples, like the early days of Mark Zuckerberg, the creators of Obsidian, or even Mr. Levels.
On the dark side. Whether that can be sustainable enough -- it's a different story. If the technopreneurs are genuinely talented, they can beef up the speed of innovation and continue the steam. However, for the company to succeed and expand in the market, it needs to grow at some point. Still, if the company relies too profoundly on its founders, it may be easier to decouple the product from the technopreneurs.
Also, knowledge can be a curse; sometimes, they become too technical and tend to create a product that leans toward a specific portion of society. Technopreneurs also take certain learning curves for granted, making mass-market products impossible. In this case, think of Steve Wozniak as a technopreneur. He had the talent and could make a full-blown product, but it never would've become Apple if it weren't for Steve Jobs.
Cutting the fat does not mean falling into overconfidence. It's a good thing that entrepreneurs have a technical background, but superhero technopreneurs rarely exist.
Backlinks (3)
IndexI 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