General Robots

General Robots Substack explores the journey of creating a general-purpose robot company, focusing on combining machine learning with robotics, problem-solving in creating robots for human spaces, and software practices for robotics. It provides insights into overcoming technical and market challenges, to achieve productivity and innovation in robotics.

Machine Learning in Robotics Software Development Practices Robotics Industry Challenges Product Development and Prototyping Technical Problem Solving Market Strategy for Robotics

The hottest Substack posts of General Robots

And their main takeaways

Dimension Hopper Part 1

395 HN points • 12 Jun 23
🕹 Technology AI Gaming Art ML Generative
  1. The project involves creating a 2D platformer where players design levels and AI generates visual representations.
  2. The journey to achieve this project involved experimenting with different techniques and models, such as adjusting depth images and adding more detail to improve visual outcomes.
  3. Using the right control images, supporting structures, and techniques like adding adjustable roughness, greatly improved the quality of the generated images.

Bonus: Art Process

104 implied HN points • 11 Jul 23
🎨 Art & Illustration
  1. Illustrations can be an integral part of essay writing.
  2. Using tools like ReMarkable2 tablet and AI assist for art creation.
  3. Iterative process involving coloring services and touch-ups.

Writing Libraries for AIs to Use

2 HN points • 12 Jul 23
🕹 Technology Artificial Intelligence Coding Programming Machine Learning Documentation
  1. Programs, libraries, and programming languages that are compatible with efficient AI assistance are likely to be favored over abstractions LLMs struggle with.
  2. Using AI assistance like ChatGPT and Github Copilot can significantly boost productivity in coding tasks, especially for less experienced programmers or when working in unfamiliar domains.
  3. LLMs excel at pattern matching, but struggle with newer or less common patterns; providing examples and good documentation can greatly improve LLM performance.
Get a weekly roundup of the best Substack posts, by hacker news affinity:

Announcing posetree.py: Wrangling Timestamps and Transforms for Robots

2 HN points • 10 Jul 23
🕹 Technology Robotics Programming Open Source Mathematics Software Development
  1. Posetree.py is a library for dealing with poses and transforms in robotics, making code more readable and reducing common bugs.
  2. Understanding the distinction between transforms, poses, and frames is crucial for clarity in robotics code.
  3. The 'timestamps' capability of posetree.py allows for expressing powerful ideas with simple code by automatically handling frame motion.

Why Build a Robot Company?

2 HN points • 06 Feb 23
  1. The key to human flourishing has shifted from land to labor to now robotics.
  2. To succeed in building a robot company, focus on making robots work in human spaces.
  3. Automating tasks, not jobs, can often lead to increased productivity and job demand.

So You Want To Do Robots, Part 2: What do you need to invent?

1 HN point • 09 Feb 23
  1. The main goal in creating robots is to make them work in human spaces.
  2. The dexterity problem is critical in making robots function effectively in human environments.
  3. Advancements in machine learning for vision have significantly improved, providing new possibilities for solving dexterity problems.