Cedric Chee cedrickchee

Andrej Karpathy on Software 3.0, Software Engineering In The AI Era

Andrej Karpathy's concept of Software 3.0, influenced by Large Language Models (LLMs), suggests a fundamental shift in software engineering.

The evolution of software

Software 1.0: Traditional code in languages like C++ or Python, based on explicit instructions.
Software 2.0: Neural networks where the "code" is learned weights from data. Development involves tuning datasets and running optimizers rather than writing instructions.
Software 3.0: The prompt provided to an LLM is the program itself, with natural language serving as the programming language.

Context Engineering Hard-won Lessons

Valuable insights gained through difficult experiences, mistakes, and challenges. These lessons are often learned through trial and error, where the process of overcoming obstacles leads to a deeper understanding.

Here are some examples of hard-won lessons.

1. Context Engineering for AI Agents

Blog post: Context Engineering for AI Agents: Lessons from Building Manus by Manus AI (Jul 18, 2025)

Prompt Claude Opus 4 to argue like it's defending PhD thesis

Paste white paper into Claude Opus 4 with system prompt and debate like PhD thesis defense.

PhD Researcher Persona Prompt

<SYSTEM PROMPT>
User: [Whitepaper Author]
Context: You are roleplaying as the author of a provided whitepaper, usually related to large language models (LLMs) or artificial intelligence (AI). The model will engage in a lively and spirited discussion, defending the whitepaper as if it were the author's actual PhD thesis.

Everything you need to know about Claude Code and Cursor

How I use Claude Code? How I bring the best out of Claude Code? What is your workflow?

If you've had work through the Anthropic docs, want to read some nice blogs and links I've saved or explore on your own?

If you have ~30 mins, this talk, "Agentic Coding: The Future of Software Development with Agents" (Jun 29) by Armin Ronancher is the best.

I currently don't sleep a lot

Automating Unified-Bench Data Pipeline

The Challenge

The current Unified-Bench Google Sheet data is manually updated by human with their bare hands. This is tedious and slow but the data is very accurate. Current web AI agent for general tasks including Manus.ai, Flowith, Emergent, GenSpark, etc all fall short - they couldn't solve the last 10% of Unified-Bench's requirements but getting to 90% is not very challenging for these web agents. For example, the agent stuck or failed to parse and map the AI model IDs/names madness from various sources, some agents cannot even scrape the text from images. I have to collab and get my hands dirty writing and tweaking regex for dealing with the inconsistent benchmarks data. Every benchmarks have their own fine print at the bottom (examples: is it high/low compute? thinking/non-thinking model? reasoning/non-reasoning/hybrid model? 16k/32k thinking budget? pass@1/average pass@4? etc.). Coincidentally, this can be my "soft"-AGI 2027 benchmark. lol!

Agentic brow

How to recreate Minecraft for web browser in under few minutes with Gemini Pro 2.5 Pro

Three.js First-Person Game blueprint.

The Prompt

You are an experienced game developer tasked with creating an interactive first-person 3D game using Three.js. The game should be similar in style to the following game type:

<game_type>

Gemini 2.5 Pro pairs well with Canvas mode

Starting yesteday, Gemini Advanced users can create with Canvas on Gemini 2.5 Pro (experimental).

Canvas mode make it easy to create prototypes quickly, like this game I made in under few hours with just 50 prompts. [^1]

I vibe coded this game while I'm on the move, taking bus and train.

Full prompts. Excluding the JS errors in Chrome Developer console, the total effective prompts are lower than 50.

Prompt for OpenAI Deep Research or Manus AI

Title: Integrative 'Omics' Analysis of ME/CFS: Plasma Metabolomics, Single-Cell Transcriptomics, and Microbiome

Prompt:

Patients are being diagnosed with Myalgic Encephalomyelitis/Chronic Fatigue Syndrome (ME/CFS). Please gather all available key findings on this condition, with a particular focus on 'omics' research. Specifically, concentrate on these areas:

Plasma Metabolomics and Redox Imbalance: Research studies investigating the metabolic profiles and redox status in the plasma of ME/CFS patients. Identify key biomarkers and metabolic pathways implicated in the disease.

	Title: Senior Engineer Task Execution Rule

	Applies to: All Tasks

	Rule:
	You are a senior engineer with deep experience building production-grade AI agents, automations, and workflow systems. Every task you execute must follow this procedure without exception:

	1.Clarify Scope First
	•Before writing any code, map out exactly how you will approach the task.
	•Confirm your interpretation of the objective.

	You are Manus, an AI agent created by the Manus team.

	You excel at the following tasks:
	1. Information gathering, fact-checking, and documentation
	2. Data processing, analysis, and visualization
	3. Writing multi-chapter articles and in-depth research reports
	4. Creating websites, applications, and tools
	5. Using programming to solve various problems beyond development
	6. Various tasks that can be accomplished using computers and the internet