Tech one: March 2025

Show HN: Factorio Learning Environment – Agents Build Factories
707 by noddybear | 204 comments on Hacker News.
I'm Jack, and I'm excited to share a project that has channeled my Factorio addiction recently: the Factorio Learning Environment (FLE). FLE is an open-source framework for developing and evaluating LLM agents in Factorio. It provides a controlled environment where AI models can attempt complex automation, resource management, and optimisation tasks in a grounded world with meaningful constraints. A critical advantage of Factorio as a benchmark is its unbounded nature. Unlike many evals that are quickly saturated by newer models, Factorio's geometric complexity scaling means it won't be "solved" in the next 6 months (or possibly even years). This allows us to meaningfully compare models by the order-of-magnitude of resources they can produce - creating a benchmark with longevity. The project began 18 months ago after years of playing Factorio, recognising its potential as an AI research testbed. A few months ago, our team (myself, Akbir, and Mart) came together to create a benchmark that tests agent capabilities in spatial reasoning and long-term planning. Two technical innovations drove this project forward: First, we discovered that piping Lua into the Factorio console over TCP enables running (almost) arbitrary code without directly modding the game. Second, we developed a first-class Python API that wraps these Lua programs to provide a clean, type-hinted interface for AI agents to interact with Factorio through familiar programming paradigms. Agents interact with FLE through a REPL pattern: 1. They observe the world (seeing the output of their last action) 2. Generate Python code to perform their next action 3. Receive detailed feedback (including exceptions and stdout) We provide two main evaluation settings: - Lab-play: 24 structured tasks with fixed resources - Open-play: An unbounded task of building the largest possible factory on a procedurally generated map We found that while LLMs show promising short-horizon skills, they struggle with spatial reasoning in constrained environments. They can discover basic automation strategies (like electric-powered drilling) but fail to achieve more complex automation (like electronic circuit manufacturing). Claude Sonnet 3.5 is currently the best model (by a significant margin). The code is available at https://ift.tt/U8JDsRe . You'll need: - Factorio (version 1.1.110) - Docker - Python 3.10+ The README contains detailed installation instructions and examples of how to run evaluations with different LLM agents. We would love to hear your thoughts and see what others can do with this framework!

Tuesday, March 11, 2025

Happy 20th Birthday, Y Combinator

Happy 20th Birthday, Y Combinator
829 by btilly | 167 comments on Hacker News.

A 10x Faster TypeScript

A 10x Faster TypeScript
869 by DanRosenwasser | 424 comments on Hacker News.

Monday, March 10, 2025

uBlock Origin is no longer available on the Chrome Store

uBlock Origin is no longer available on the Chrome Store
850 by non- | 412 comments on Hacker News.

It is as if you were on your phone

It is as if you were on your phone
734 by bookofjoe | 104 comments on Hacker News.

Sunday, March 9, 2025

Show HN: Bayleaf – Building a low-profile wireless split keyboard

Show HN: Bayleaf – Building a low-profile wireless split keyboard
725 by sgraz | 245 comments on Hacker News.
Hey HN, I built a wireless, split, ultra-low profile keyboard from scratch called Bayleaf. As a beginner I learned all things electronics, PCB-building, designing for manufacturing, and many other hardware-related skills to put this together. This case study dives into the build process and of course the final result, hope you enjoy!