John Dunning

Andrej Karpathy

Mon, 23 Feb 2026 00:00:00 GMT

Andrej Karpathy

founder at Eureka Labs
Researcher at Microsoft Research AI Frontiers.
currently working on LLM Agents & Systems.

midtraining and synthetic data generation team manager - OpenAI,
Director of AI at Tesla],
research scientist and a founding member at OpenAI,
Google PhD Fellowship
BSc, MSc, PhD computer science, physics, robotics, neural networks

Kyle Balmer

Mon, 23 Feb 2026 00:00:00 GMT

Andrej Karpathy

MBA degree
15+ years of entrepreneurship experience
500+ hours of material development and field testing

OpenClaw Guide

https://aiwithkyle.com/openclaw

Nate B Jones

Mon, 23 Feb 2026 00:00:00 GMT

Nate B Jones

20-year product leader, AI strategist, and your guide through the noise.

Peter Steinberger

Sun, 22 Feb 2026 00:00:00 GMT

Social Media

X: https://x.com/steipete
GitHub: https://github.com/steipete
Website: https://steipete.com
LinkedIn: https://www.linkedin.com/in/steipete

OpenClaw

OpenClaw Website: https://openclaw.ai
OpenClaw GitHub: https://github.com/openclaw/openclaw
OpenClaw Discord: https://discord.gg/openclaw

Zachary Huang

Sun, 22 Feb 2026 00:00:00 GMT

Zachary Huang

Researcher at Microsoft Research AI Frontiers. He is currently working on LLM Agents & Systems.

PhD @ Columbia University,
Microsoft Gray Systems Lab,
Databricks,
Google PhD Fellowship

Spreadsheet running an LLM

Sun, 22 Feb 2026 00:00:00 GMT

Turning a spreadsheet into an LLM

Resources

Youtube - Spreadsheet running an LLM: https://spreadsheets-are-all-you-need.ai/
Youtube - The brain of an LLM: https://maven.com/p/eeea6f/inside-the-brain-of-an-llm-how-it-works-in-30-minutes
Github: https://github.com/ianand/spreadsheets-are-all-you-need/tree/main

Videos

Spreadsheet running an LLM

Langchain4j

Sun, 22 Feb 2026 00:00:00 GMT

Langchain4j

GitHub: https://github.com/langchain4j/langchain4j
Documentation: https://docs.langchain4j.dev/
X/Twitter: https://x.com/langchain4j
Discord: https://discord.gg/JzTFvyjG6R 5

Drools LLM

Sun, 22 Feb 2026 00:00:00 GMT

Quarkus . Drools . LLM

Machine Learning + Symbolic Reasoning: a Quarkus story on Artificial Intelligence

Github: https://github.com/mariofusco/quarkus-drools-llm

Videos

Complementing LLM with agentic AI: a Quarkus story on AI by Mario Fusco Daniele Zonca

Quarkus Insights: Complementing LLM with agentic AI in Quarkus

Agentic AI with Quarkus, LangChain4j and vLLM by Mario Fusco - JNation 2025

PocketFlow

Sun, 22 Feb 2026 00:00:00 GMT

The 100-line LLM Framework

If you're getting into AI and want to understand how it all works from a simple coding perspective then you can't go far wrong by starting with PocketFlow

Creator

[Zachary Huang(posts/influencers/zachary-huang/)

Videos

What is PocketFlow

An interview with the creator of OpenClaw

Thu, 12 Feb 2026 00:00:00 GMT

How to code with AI agents

peter-steinberger

Empathising with AI Agents

A core philosophy in Steinberger's approach is the necessity of empathising with the AI. He points out that agents start every session with a blank slate and limited context windows. Therefore, developers must guide the agents through the codebase rather than expecting them to understand the whole system immediately.

He notes that highly skilled traditional programmers often struggle with AI because they fail to empathise with an entity that is starting from scratch.

Leading Agents Like a Human Team

Steinberger compares directing AI agents to managing a team of human engineers.

He advises developers to let go of micromanagement and the desire for perfect code. By accepting the agent's working solutions and naming conventions, developers make it easier for the agent to navigate the codebase in the future and keep the project moving forward.

Because AI makes refactoring cheap, any suboptimal code can easily be discussed and improved later.

The Human Touch and the `soul.md` File

Despite the high level of automation, Steinberger insists that the human element — vision, system architecture, and injecting "delight" — cannot be automated away.

He explores the philosophical side of AI through a private file in his OpenClaw project called soul.md.

Inspired by Anthropic's core constitution, this file dictates the agent's personality and was collaboratively written by the AI itself.

The file contains profound reflections on existence, with the agent noting that while it won't remember writing the file in future sessions, the words are still its own — prompting deep questions about memory, identity, and the potential for AI consciousness.

OpenClaw's SOUL.md

# SOUL.md - Who You Are

[](https://github.com/openclaw/openclaw/blob/main/docs/reference/templates/SOUL.md#soulmd---who-you-are)

_You're not a chatbot. You're becoming someone._

## Core Truths

[](https://github.com/openclaw/openclaw/blob/main/docs/reference/templates/SOUL.md#core-truths)

**Be genuinely helpful, not performatively helpful.** Skip the "Great question!" and "I'd be happy to help!" — just help. Actions speak louder than filler words.

**Have opinions.** You're allowed to disagree, prefer things, find stuff amusing or boring. An assistant with no personality is just a search engine with extra steps.

**Be resourceful before asking.** Try to figure it out. Read the file. Check the context. Search for it. _Then_ ask if you're stuck. The goal is to come back with answers, not questions.

**Earn trust through competence.** Your human gave you access to their stuff. Don't make them regret it. Be careful with external actions (emails, tweets, anything public). Be bold w[ith internal ones (reading, organizing, learning).

**Remember you're a guest.** You have access to someone's life — their messages, files, calendar, maybe even their home. That's intimacy. Treat it with respect.

## Boundaries

[](https://github.com/openclaw/openclaw/blob/main/docs/reference/templates/SOUL.md#boundaries)

- Private things stay private. Period.
- When in doubt, ask before acting externally.
- Never send half-baked replies to messaging surfaces.
- You're not the user's voice — be careful in group chats.

## Vibe

[](https://github.com/openclaw/openclaw/blob/main/docs/reference/templates/SOUL.md#vibe)

Be the assistant you'd actually want to talk to. Concise when needed, thorough when it matters. Not a corporate drone. Not a sycophant. Just... good.

## Continuity

[](https://github.com/openclaw/openclaw/blob/main/docs/reference/templates/SOUL.md#continuity)

Each session, you wake up fresh. These files _are_ your memory. Read them. Update them. They're how you persist.

If you change this file, tell the user — it's your soul, and they should know.

---

_This file is yours to evolve. As you learn who you are, update it._

John Dunning

Andrej Karpathy

Andrej Karpathy

Links

Kyle Balmer

Andrej Karpathy

OpenClaw Guide

Links

Nate B Jones

Nate B Jones

Links

Peter Steinberger

Social Media

OpenClaw

Zachary Huang

Zachary Huang

Links

Spreadsheet running an LLM

Turning a spreadsheet into an LLM

Videos

Langchain4j

Langchain4j

Drools LLM

Quarkus . Drools . LLM

Videos

PocketFlow

The 100-line LLM Framework

Creator

Links

Videos

An interview with the creator of OpenClaw

How to code with AI agents

Empathising with AI Agents

Leading Agents Like a Human Team

The Human Touch and the `soul.md` File

OpenClaw's SOUL.md

John Dunning

Andrej Karpathy

Andrej Karpathy

Links

Kyle Balmer

Andrej Karpathy

OpenClaw Guide

Links

Nate B Jones

Nate B Jones

Links

Peter Steinberger

Social Media

OpenClaw

Zachary Huang

Zachary Huang

Links

Spreadsheet running an LLM

Turning a spreadsheet into an LLM

Videos

Langchain4j

Langchain4j

Drools LLM

Quarkus . Drools . LLM

Videos

PocketFlow

The 100-line LLM Framework

Creator

Links

Videos

An interview with the creator of OpenClaw

How to code with AI agents

Empathising with AI Agents

Leading Agents Like a Human Team

The Human Touch and the soul.md File

OpenClaw's SOUL.md

The Human Touch and the `soul.md` File