• AutoBuilder

Cursor is incredibly good harness.

Opus is also not Oputhetic anymore

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

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

Auto Refactor

Prompt

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

--completion-promise "KARPATHY_WILL_APPROVE_EVERY_SINGLE_LOC_FOR_SURE"

Auto Fixer

Prompt

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

--completion-promise "NO_COMMENTS_REMAINING_IN_GITHUB_EVEN_AFTER_20_MINUTES"

Auto Builder

Prompt

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

--completion-promise "NO_REMAINING_TASK_AND_KARPATHY_APPROVES_EVERY_SINGLE_LOC_IN_ITS_ENTIRETY"

Common Element

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>

Project Linguine is an initiative to define a deterministic list (i.e., the Linguine Recipe) to cover all linguistic Sprachraum. That is,

How many people around the world do not speak any of the languages defined in Linguine?

... should be near zero.

Candidates are...

• BCP 47
• Ethnologue 200
• DeepL
• Google Translate

Supporting Ethnologue 200 is too much. Also, for BCP 47, it's not only unfair but also excessive to translate for en-US, en-CA, and en-GB separately. So we agree that a linguistic Sprachraum should be simplified, yet considering variants like Taiwanese (zh-TW is different from zh-CN)

Do we still need to support i18n? It's an extra bunch of costs, not going to lie. But technology is in an exceptional stage, where people from all regions are flying to silicon valley for a better life. People seek information worldwide, and considering those, backfilling the data would be relatively easy. It's laying out fisher rods worldwide, with just an extra cost.

After looking into the subscriber lists of hn.cho.sh, I did notice that there are bogus subscriber lists. For example, I have no authentic Finnish subscribers. However, I want to keep the window open for international free minds to find the service. For example, I got an email from an Italian subscriber:

I found the service thanks to the advertisement in your extension of Bing Chat for All Browsers. This service is very innovative, and I especially love the fact that it is in my language. I will certainly share this news with my friends who are tech enthusiasts. The first time I visited the site, I had the amazing feeling of being catapulted into the kind of future I've always dreamed of but never seen realized. Thank you for providing such a fantastic experience! Make the web truly innovative!

The most important thing is to keep the net service profit, or net neutral at least. At this burn rate, we cannot continue the service.

DeepL vs Google Translate vs Bing Translate Offering Comparison

So, in conclusion:

1. Use the following list.

2. For Curated Newsletters, you cannot sign up for more than three locales. This is to prevent bogus subscribers.
3. As such, we will have zero subscribers for Finnish, for example, because we have yet to have an actual customer. We will still translate the top 3 articles for advertisement and the 'magical landing experience.'
4. There can be a button to request translation. Maybe this can be a pro feature?

While comparing offerings, I found that nb and no are both used in the Norwegian Langauge. Interesting.

230713

Linguine Engine Test Drive Result 2023-07-13