software-paradigms-karpathy
Skill8 starsChanged 10 months agoNo licenceView on GitHub
Explains Andrej Karpathy's framework for understanding the three paradigms of software (1.0- traditional code, 2.0- neural network weights, 3.0- LLM prompts). Use when users ask about software paradigm shifts, the evolution of programming, how LLMs fit into software development history, Software 1.0/2.0/3.0 distinctions, prompt engineering as programming, or when they need to explain or apply Karpathy's mental model for understanding modern AI development. Also useful when discussing how to think about building software in the AI era, choosing between traditional code vs neural nets vs LLM prompts, or explaining the significance of "programming in English.
In this repository18 other files it gives its agents.
- agi-framework-cholletSkill
- ai-accelerated-building-ngSkill
- ai-product-building-hellerSkill
- ai-scaling-laws-amodeiSkill
- ai-scientific-discovery-jumperSkill
- ai-search-strategy-srinivasSkill
- ai-startup-insights-altmanSkill
- ai-startup-questions-fisherSkill
- b2b-ai-startup-levieSkill
- claude-code-best-practicesSkill
- design-tool-scaling-fieldSkill
- developer-tools-strategy-truellSkill
- enterprise-ai-strategy-nadellaSkill
- first-principles-thinking-muskSkill
- robotics-ai-learning-finnSkill
- software-democratization-masadSkill
- spatial-intelligence-liSkill
- yc-startup-fundamentalsSkill
The file
We split this skill into the rules it gives an agent
4 rules. About 0 are common, 4 are distinctive, and 0 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈4
Distinctive · estimate
This author's own choices. Worth a look.
0
Very specific
Tied to their project's names, files or tools. Probably skip.
No licence file, so all rights are reserved — read it at the source. We count its rules but don't quote them. Read them on GitHub.
≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.