# OpenClaw creator's programming setup | Peter Steinberger and Lex Fridman Source: https://www.youtube.com/watch?v=m_l9pUKLiXo Recap page: https://rapidrecap.app/video/m_l9pUKLiXo Generated: 2026-02-18T13:33:32.137+00:00 --- ## Quick Overview The creator of OpenClaw, Peter Steinberger, explains that his complex programming setup, featuring around 17 computers/monitors, is essential for his workflow because it allows him to see multiple context windows simultaneously, which is necessary when dealing with undocumented or difficult-to-read codebases like the one he is currently working on, although he admits that modern tools like Claude (LLM) could potentially reduce the need for such extensive hardware. **Key Points:** - Peter Steinberger uses an extensive setup involving approximately 17 screens across 10 different Apple devices (MacBooks and iPads) to manage his complex development workflow. - The setup is designed to allow him to view multiple context windows simultaneously, which is crucial when dealing with large, poorly documented, or unfamiliar codebases. - He mentions using the 'plan mode' feature, which helps guide development by showing what needs to be done, rather than just writing code blindly. - Steinberger notes that he often asks the AI (implied to be Claude or similar LLM) questions about the code, and then reads the answers to understand gaps in his knowledge. - He finds that while modern LLMs are helpful, they don't entirely replace the need for extensive screen real estate when refactoring or debugging complex legacy code. - Steinberger admits that when he first started, he made mistakes like confusing development folders, leading to significant time loss. - He prefers this multi-screen, text-heavy workflow over modern LLM-assisted development processes that rely on a more minimal interface, finding the latter slow and unnecessary for his current tasks. ![Screenshot at 00:21: Peter Steinberger's complex programming setup, featuring approximately 10 visible screens \(laptops and external monitors\) displaying code and documentation, which he uses to maintain maximum contextual awareness during development.](https://ss.rapidrecap.app/screens/m_l9pUKLiXo/00-00-21.jpg) **Context:** This segment of the Lex Fridman Podcast features an interview with Peter Steinberger, the creator of OpenClaw, a tool for managing transaction data for cryptocurrency. The discussion centers on Steinberger's highly specialized and extensive programming setup, which he uses to manage complex software projects, particularly when dealing with legacy code or when aiming for deep code comprehension through contextual awareness. ## Detailed Analysis Peter Steinberger discusses his elaborate programming setup, which he humorously contrasts with the idea of a minimalist workflow, revealing he uses about 17 screens across several MacBooks and iPads. He explains that this massive visual surface area is necessary because he frequently works on large, undocumented codebases, citing the need to keep multiple context windows open simultaneously to understand what he is reading and what needs refactoring. He mentions that while he likes using AI tools like Claude to ask specific questions about the code, he still finds the visual context provided by many screens invaluable for understanding the architecture and finding knowledge gaps. He recounts past mistakes, like accidentally running processes in the wrong project folder, emphasizing the importance of clear context. He contrasts his method with the modern approach where AI might suggest refactoring or writing tests, stating that for complex code, he still needs to see everything at once to effectively refactor or understand the 'ghosts' in the system, even though he acknowledges that the AI context might eventually reduce this need. He concludes by noting that his current setup allows him to give the AI context for its answers, rather than just asking broad questions. ### Programming Setup & Workflow - The setup involves approximately 17 screens across 10 Apple devices (MacBooks/iPads) - Essential for maintaining context across large, undocumented codebases - Steinberger prefers this visual density over newer, minimalist AI-driven workflows. ### AI Integration - He uses AI (like Claude) to ask specific questions about the code to fill knowledge gaps - He feels the AI needs context from his extensive setup to provide the best answers - He avoids asking the AI to just 'write code' or 'refactor' without providing context first. ### Development Process - He uses 'plan mode' to organize tasks and identify what needs refactoring - He recounts past errors like confusing project folders, highlighting the risk of poor context management. ### Refactoring Philosophy - He often asks the AI what parts of the code are not optimal or what files he should look at for documentation - He emphasizes understanding the existing codebase before making changes, even if it takes significant time. ![Screenshot at 00:21: Peter Steinberger's complex programming setup, featuring approximately 10 visible screens \(laptops and external monitors\) displaying code and documentation, which he uses to maintain maximum contextual awareness during development.](https://ss.rapidrecap.app/screens/m_l9pUKLiXo/00-00-21.jpg) ![Screenshot at 00:03: Lex Fridman preparing to speak into his microphone in the podcast studio setting.](https://ss.rapidrecap.app/screens/m_l9pUKLiXo/00-00-03.jpg) ![Screenshot at 00:19: The guest, Peter Steinberger, smiling and gesturing while discussing his setup.](https://ss.rapidrecap.app/screens/m_l9pUKLiXo/00-00-19.jpg) ![Screenshot at 02:01: A close-up of the terminal/code view on Steinberger's multi-monitor setup, showing dense text and color-coded output.](https://ss.rapidrecap.app/screens/m_l9pUKLiXo/00-02-01.jpg) ![Screenshot at 00:40: Lex Fridman listening intently to the discussion, resting his hand near his face.](https://ss.rapidrecap.app/screens/m_l9pUKLiXo/00-00-40.jpg)