If you sit to code today pick one of two `modes` you are in -
1. Learning mode - turn off ai, read docs, spend time doing tough problems, gratification is learning something new and not the speed of implementation.
2. Implementation mode - Coding tools (cursor etc) have gotten really good. Make it cruise through writing code while you watch netflix or sm.
2 is more fun if you've spent a few hours doing 1.
Programming languages and what they’re built with
• C → Written in Assembly
• C++ → Written in C
• Java → Written in C++
• Python → Written in C
• JavaScript (V8 engine) → Written in C++
• Go → Written in C (initially), now mostly Go
• Rust → Written in Rust (bootstrapped from OCaml)
• TypeScript → Written in TypeScript
• Kotlin → Written in Kotlin
• Swift → Written in C++
• PHP → Written in C
• Ruby (MRI) → Written in C
• C# → Written in C++
• Dart → Written in C++
• Scala → Written in Scala
• Haskell (GHC) → Written in Haskell
• Elixir → Written in Elixir (runs on Erlang VM)
• Erlang → Written in C
• Zig → Written in Zig
• Bash → Written in C
• Lua → Written in C
• Julia → Written in Julia + C
• R → Written in C + Fortran
• Objective-C → Written in C
Repetition changes your brain.
Repetition changes your brain.
Repetition changes your brain.
Repetition changes your brain.
Repetition changes your brain.
Repetition changes your brain.
Repetition changes your brain.
That’s why it works.
You don't need to spend a single dollar to build a production AI system in 2026.
Here's the full stack:
→ LLM: Ollama + Gemma 4 / Llama 3.3 / Mistral Small 4 (local, free)
→ Orchestration: LangGraph / CrewAI (open source)
→ RAG: LlamaIndex + ChromaDB / Qdrant (local)
→ Tool Layer: MCP — the open protocol connecting agents to everything
→ Code Agent: Claude Code CLI / Aider
→ Frontend: Next.js + Vercel free tier / Streamlit
→ Data: SQLite / DuckDB / Supabase free tier
→ Observability: Langfuse / Phoenix (self-hosted)
→ Deploy: Docker / Cloudflare Workers / HuggingFace Spaces
Total cost → $0.
The tools are free.
The architecture knowledge is what's valuable.
Save this for your next build 🔖
Credit: codewithbrij
#AIArchitecture #AgenticAI #LLM #Ollama #Gemma4 #LangGraph
This 2 hour Stanford lecture will teach you more about how LLMs like ChatGPT & Claude are built than most people working at top AI companies learn in their entire careers.
Bookmark this & give 2 hours today, no matter what. It'll be the most productive thing you do this week.
Wanna become a C++ expert? Good news, everyone!
Join CodeCrafters and build your own low-latency in-memory DB.
And because you endured all my shitposts, you get a generous 40% discount. I reward your loyalty.
https://t.co/lt0bXZog78
It's time to git gud. #ad