Codex builds a working NES Emulator in one hour
Hi folks! I know NES emulators have been implemented countless times, in practically every language imaginable. However, having an LLM fully replicate the spec purely from memory—without referencing existing code—is still a significant challenge. It requires the underlying model to have strong anti-hallucination capabilities and solid long-term planning to keep from going astray. Because of this, building an NES emulator makes for an excellent LLM stress test. Here is how the emulator was built: Data Gathering: I asked Codex to download the necessary developer manuals and test suites. It was…
What it does
In the maker’s words, at launch
Hi folks! I know NES emulators have been implemented countless times, in practically every language imaginable. However, having an LLM fully replicate the spec purely from memory—without referencing existing code—is still a significant challenge. It requires the underlying model to have strong anti-hallucination capabilities and solid long-term planning to keep from going astray. Because of this, building an NES emulator makes for an excellent LLM stress test. Here is how the emulator was built: Data Gathering: I asked Codex to download the necessary developer manuals and test suites. It was strictly prohibited from searching for reference implementations online. Development: I instructed Codex to build the emulator until all test suites passed. This process was mostly hands-free; I only chimed in to encourage it to continue when it paused. First Draft: After just 4-5 prompts, Codex delivered a functional, pure-Python emulator—though it ran at a sluggish 7 FPS. Optimization: Asking Codex to optimize the app completely on its own didn't work this time. Instead, I had it generate a flamegraph, which identified the PPU update as the bottleneck. I then instructed Codex to rewrite the PPU in Cython without breaking the passing tests. Overall, I'm incredibly impressed by Codex. I already knew it was capable of the task, but the speed was astonishing. It finished the project in under an hour, using merely 2% of my weekly Pro quota. While the NES might be a relatively easy system to emulate, I think emulation could serve as a fantastic benchmark for testing future LLMs.
Does the same job
all alternatives →- ANAn NES emulator written in Rust2013 · github.com · ▲125
- CACycle-accurate Nintendo NES emulator in ~1000 lines of code2016 · github.com · ▲20
- ANA NES Emulator Written in Emacs Lisp2019 · github.com · ▲10
- ALAn LLM Running on a PS Vita2025 · github.com · ▲5
Hello all, a couple of moons ago I ported karpathy's llama2.c code to run inference on the TinyStories 260K & 15M checkpoints on the on the PS Vita with the ability to download/delete the models on device. Runs showed that the 260K model ran at ~120 tok/s and at 15M ran at 1.8 tok/s, which probably could be a bit higher if it weren't a single threaded application. Had fun working on it as a weekend project, check it out for yourselves: https://github.com/callbacked/psvita-llm
- IBI built an open-source alternative to the "brainrot IDE" that YC fundedDec 2025 · github.com · ▲6
VSCode extension with games (Snake, Plinko, slots), HN/LessWrong reader, and Pomodoro timer for AI coding wait times. Fake currency only. Marketplace: https://marketplace.visualstudio.com/items?itemName=TouchGra... Built in a week with Claude Code after seeing Chad IDE get ratio'd for integrating real gambling. Happy to answer questions or get roasted on the code.
More ai this month
the category →
I trained a 125M-parameter transformer to autocomplete piano performances in real time (~108 notes/sec on an iPhone 15). The idea is basically GitHub Copilot or Tabnine, except instead of prompting it with code, you prompt it by playing a few notes on a MIDI piano. The model then continues what you played, entirely on-device. The app is free if anyone wants to try it. Happy to answer questions about the model, training, Core ML, or the many things that didn't work.
AI · 17d ago · simedw.com
Astute▲585Automate your B2B brand going viral, with new media creators
AI · 18d ago · company-app.joinastute.com
Hey HN, Henry from Cactus here! We previously released Cactus Needle, a 14MB agentic LLM for tool call, device use, and structured extraction for phones, wearables, smart homes, small robots and microcontrollers. We got really great feedback here, and have now incorporated the suggestions to release Needle 2. The whole model is a single 14MB binary that runs a full session in 28MB of RAM; 45m parameters at 2bit compression. Needle hits 500 tokens/sec decode speed on a Raspberry Pi 5, sits between 400-1,500 tokens/sec on VR devices like Meta Quest 3S and Apple Vision Pro, and ranges…
AI · 27d ago · cactuscompute.com
