AI Agents AI Gadgets & HW AI Models - LLM AI Open Source AI Security AI for Coding AI for Gaming AI for Images AI for Music AI for Videos Artificial Intelligence Editor's Choice NVIDIA AI Other News Robotics Tech Face-off Tech Satire

AI-Generated Super Smash Bros PC Port Lands as BattleShip Beta

By Artūras Malašauskas Apr 30, 2026 4 min read Share:
Developer JRickey released BattleShip, an unofficial native PC port of Super Smash Bros (N64) claiming 100% AI-generated code, though it relies on existing decompilation work.

A native PC port of the original Super Smash Bros. has arrived, and the developer claims it was created entirely using artificial intelligence. The project, titled BattleShip, was released by developer JRickey as a beta build on GitHub.

The port is built on top of the VetriTheRetri/ssb-decomp-re decompilation project, which is reportedly 99.7% complete. It uses libultraship for PC-native rendering, audio, and input layers, along with Torch for extracting assets from the ROM at build time. According to the project's README, the repository is a pure C/C++ source tree that extracts every byte of Nintendo-owned data from a user-supplied ROM.

JRickey states the port is "100% AI-generated" and took approximately 25 days to complete. The developer credits Opus 4.6, Opus 4.7, and GPT 5.5 as the only contributors alongside themselves. At various points during development, AI agents were dispatched to build and test autonomously while the developer handled other tasks.

However, the "100% AI-generated" claim requires context. JRickey explicitly notes that years of work from many people went into the decompilation, the 3D engine, asset extraction, and everything else this port stands on. The AI was not given an N64 cartridge and asked to produce a PC port from scratch. Instead, it accelerated the integration work on top of an existing foundation.

The port requires the NTSC-U v1.0 ROM of Super Smash Bros. for the Nintendo 64. Users must supply their own legally obtained ROM to build and run the project. The GitHub repository includes the required SHA-1 and MD5 hashes for the correct ROM dump. This approach means the repository itself contains no Nintendo assets.

From a legal standpoint, this distinction matters significantly. Multiple outlets report that because the repository does not contain Nintendo's copyrighted assets, the company would have limited grounds to force a takedown. The project follows the same pattern as other native PC ports of Nintendo 64 classics that have emerged in recent years.

Functionally, the beta build launches and runs on PC. Single-player Classic Mode is playable, and the game can achieve 60 frames per second. However, reviewers note the build is not feature-complete and may contain bugs. It is by no means fully playable or stable at this stage.

The physical experience differs from emulation in meaningful ways. Native ports like BattleShip offer higher resolution support, smoother input handling, and better integration with modern PC hardware. There's no emulator overhead to contend with, and the game renders directly through PC-native APIs rather than through an emulation layer.

This release serves as a proof of concept for AI-assisted development at scale. The developer's stated goals were twofold: to learn more about how things are actually made in C, and to demonstrate that AI can be used for tasks of this magnitude. The project is intended to show that the barrier to making complex software is lower than many assume.

Industry observers note that community-native ports built on decompilation projects have become a recurring pattern for classic consoles. Projects that layer automated code generation or AI-assisted workflows on top of those foundations accelerate iteration, but they remain dependent on prior reverse-engineering work and human-maintained decompilers.

For practitioners exploring model-guided engineering, this release highlights that model-assisted development can speed integration work when a strong human-created substrate exists. It does not, however, obviate the need for domain expertise in systems programming, testing, and legal compliance.

Given the heavy reliance on AI, this project is likely to be superseded by human-made versions in time. Once Super Smash Bros. is fully decompiled, we will likely see a range of native PC porting projects emerge. These could include versions with 16:9 widescreen support, higher framerate capabilities, and modded versions with additional characters.

The question remains whether users will actually want an AI-generated port when human-crafted alternatives become available. AI has no shortage of critics, and there are undoubtedly developers who will want to create a human-made PC version of Super Smash Bros. Whether this matters to players is another question entirely.

For now, the port is available on GitHub for those who want to experiment. Whether it survives long-term depends on Nintendo's response and whether the community finds value in an AI-assembled build versus one crafted by hand. The technology works. Whether it's the right approach is still being decided.

Multiple sources have covered the release, including Wccftech and DSOGaming. Both outlets confirm the technical details and legal context surrounding the release.

Whether this represents a meaningful shift in how games are ported or just a curious experiment remains to be seen. The code exists, the game runs, and the AI did the heavy lifting. Whether that's progress or a shortcut is a debate that will continue long after the port is forgotten.

Arturas Malas Artūras Malašauskas is an AI Systems Integrator with 20+ years of production-grade web engineering experience. He has designed, shipped, and scaled enterprise Python/PHP systems for logistics, SaaS, and public-sector clients. For the past year, he has focused exclusively on AI integrations: deploying open-source LLMs, building generative media pipelines (image, audio, video), and engineering multi-agent workflows for real production environments. His standard: reproducibility, security, cost-efficient inference—no vaporware. He documents and evaluates emerging AI tooling, separating verified capabilities from marketing noise. Technical editor at: muza-ai.eu, ai-verslas.lt, ai-naujinos.lt Connect on LinkedIn
Share:

Comments

Sign in to comment:
    <