HN Showcase
Back to browse
Codex Plays NetHack

Codex Plays NetHack

by emosenkis·Jul 27, 2026·1 point·0 comments
Visit ProjectView on HN

AI Analysis

●●SolidNiche GemShip It

Transparent terminal wrapper with approval gates before AI executes commands.

Strengths
  • •User approval gate prevents AI from running destructive commands unchecked.
  • •Fully transparent wrapper keeps the human in the driver's seat.
  • •Live demo of an AI successfully navigating a complex roguelike game.
Weaknesses
  • •Currently just a demo recording; the tool itself lacks a dedicated landing page.
  • •Niche appeal limited to those interested in AI agents or NetHack specifically.
Target Audience

Developers experimenting with AI agents and terminal automation

Similar To

Aider · OpenInterpreter

Post Description

I'll add a link to the completed recording after the stream completes.

Similar Projects

AI/ML●●Solid

NetHack agent harness with benchmarks and livestream

You can watch an LLM play NetHack step-by-step with the model's reasoning, the exact action code, and a live game canvas — that instrumentation is the product's real selling point. The leaderboard + run/benchmark framing makes it useful for comparing agents rather than just a flashy demo, but it's still squarely for people who care about NetHack or agent evaluation; more detail on reproducible metrics and integrations would push it further.

Niche GemWizardry
kenforthewin
115mo ago
Gaming●Mid

Play Bang Bang against a neural network

You play a minimalist web game while a neural net trains in real time, so the opponent starts weak and adapts to your playstyle. The landing page is extremely spare — the demo is quick to load and oddly charming, but there’s little signposting about the model, implementation details, or source code. Fun as a curiosity or teaching toy, but not novel enough to wow ML folks who’ve seen in-browser learning demos before.

Niche GemCozy
atum47
105mo ago