💀 The 15-Minute Thermal Runaway (Endgame)

At exactly 15:00, all standard enemies are swept away, and the unkillable red boss Hardware Degradation arrives. You cannot harm it.

💬 Let's Discuss:

What was your longest survival time on Smart Toaster difficulty?

What architectural combination (e.g., Quantization speed boosts + Cosine Similarity) did you find most effective?

GitHub logo UnitBuilds-CC / GPU-SURVIVORS

Homage to Vampire Survivors, as an educational game to teach players about LLMs.

GPU Survivors: Latent Space Hell 📟⚡

Can you survive a 1T parameter inference run?

Welcome to GPU Survivors, an interactive 2D retro action-roguelike built to simulate the architectural limits, failure modes, and optimization hyperparameters of running a Large Language Model under load.

🎮 The Scenario

In the digital deep, bad data and chaotic vectors threaten inference stability. You are a GPU Core initializing a new language model. Survive the endless incoming waves of training loads (OOD outliers, prompt injections, and data biases), gather FLOPs (XP), and scale your architecture to 1T parameters!

⌨️ Controls

Move: Use WASD or Arrow Keys.
Pause: Press Escape or P to pause the run, resume, or exit.
Attack: Auto-targeted active weapons fire queries at the nearest token anomalies.

🛠️ Hardware Presets (Difficulty Modes)

Select your inference endpoint difficulty at startup:

🏢 ENTERPRISE API (H100 Cluster) — Easy
- Stats: 6 Core Integrity...

View on GitHub

Disclaimer: AI was used throughout this project, it is just fitting that it would co-author with me, so special thanks to the Foundry for its tireless hours toiling away and Gemini for producing the cover image.

Top comments (10)

nazar-boyko profile image

Nazar Boyko

Software engineer, backend & AI-focused. Node.js, TypeScript, Go, PHP/Laravel, AWS. I write a lot about reliable systems and AI agents that actually ship. More at nazarboyko.com

Email

boyko.nazar@gmail.com
Location

Austin, TX
Education

M.S. Computer Science
Joined

Aug 2, 2024

• Jul 5

Quick question about the KV cache orbitals. In the game they're pure defense, but in real inference the cache's whole cost is memory, so is there any downside to stacking them, like slower movement or a smaller collection radius to stand in for VRAM pressure? That would sneak the memory versus latency trade into the game almost for free. Either way, quantization as a faster fire rate for slightly lower damage is the cleanest mapping in the set, that one teaches itself.

unitbuilds profile image

UnitBuilds UnitBuilds CC

UnitBuilds

Founder of UnitBuilds CC

Location

Swakopmund, Namibia
Pronouns

He/Him
Work

Senior software Engineer (day-job), Owner of UnitBuilds (sadly second).
Joined

May 24, 2026

Good point, as a higher tier state change, that's something not covered by this early version on the series, as it's means as an A-Z guide on LLMs, for now the core concepts are isolated to their main purpose, eg. The KV-cache orbital is meant to explain how concepts that would overwhelm the model, are put into cache, where they can be interpreted for longer. While I like the idea of downside stacking, I am running the entire experience for everyone on a single core cloud-run, so limited by the resource constraints, it's as much detail as I can put in, while maintaining a usable speed for everyone. While these designs are meant to teach a concept, their real purpose is to make people ask the deeper questions, such as the consequence to quantization, beyond the obvious like higher throughput, lower quality. where training raises the damage retention, while maintaining speed boost, etc.

motedb profile image

mote

Embedded multi-modal database for edge AI

Joined

Feb 27, 2026

The game-as-concept-visualizer approach works surprisingly well here. What I like about the quantization analogy is that it gets at something the "lower precision = worse quality" framing misses: quantization noise isn't uniformly distributed. Some information degrades more than others depending on weight magnitude distributions and outlier values. INT4 on a 70B model doesn't lose the same capabilities as INT8 on a 7B â the loss profile is completely different.

The cosine similarity mapping to "move forward for bonus damage" is clever because it makes the directional nature of attention concrete. People understand that alignment matters, but tying it to spatial movement makes the asymmetry visceral.

I'm curious about SYS_02 (MoE gating network) â that's the most complex mechanic to simulate and the one with the most interesting real-world parallels. MoE load balancing is notoriously tricky because expert routing can collapse: a few "popular" experts get overloaded while others sit idle. How are you handling the adversarial scenario where a user tries to trigger expert collapse, and does it map to actual attacks on MoE systems like the mixture-of-agents attacks that have been published recently?

These series are more meant as introductory courses for people just getting into LLMs, to explain the complex behaviors and nuances in a way that is easy to digest. I try not to dig too deep into each for the early part of the series, as that would lead to overwhelming mechanics that just destroy the user's perception of it. The gating network is a simple task "route traffic amongst the MoEs", simple and easy if you make it so, but raise the rate, lower the activation threshold, tighten to 4 experts instead of 8, etc. Suddenly people can visually and emphasize with the concept of over-utilization of generalist experts, which is why it heavily biases towards 2 and 7 (if you play it enough, you'll see the pattern), this is so when the user ups it to see how fast they can do it, that they eventually hit a wall where the experts cant keep up, so suddenly a highly technical math, coding problem, gets routed to generalist and math, which inherently wont be a good combo for the task of coding, or coding and generalist, resulting in decent code, yet broken algorithms. That way the real tradeoff of going MoE (sparse) is shown to be something that is unavoidable. If a user was deciding whether or not to go MoE on a specific task, the game will make them think twice before choosing, as choosing wrong could end up costing them more than just a grammatic error, it could result in clean, tested, verified, useless code because the wrong expert assisted due to overload.

voltagegpu profile image

VoltageGPU

Sealed GPUs. Private AI. Confidential by default.

Location

France
Joined

Oct 11, 2025

• Jul 6

Scaling to 1T parameters is a beast of a problem—memory bandwidth becomes the real bottleneck long before compute. I've seen similar issues when working on model parallelism with VoltageGPU, where even small token splits could cause cascading inefficiencies in data flow. It's not just about the raw FLOPs anymore.

vicchen profile image

Vic Chen

AI builder exploring finance & institutional investing. Building tools to decode how the smart money moves. SF Bay Area.

Location

San Francisco, CA
Education

Stanford University, Computer Science
Work

Founder, building AI tools for finance
Joined

Feb 14, 2026

Really fun framing. I especially liked how you mapped cosine similarity / RAG / self-attention into gameplay instead of stopping at surface-level analogies. The quantization section was also a nice touch—explaining the speed/VRAM tradeoff as a slight damage penalty makes the production tradeoff feel intuitive. Curious if you’ll do a follow-up level around KV cache pressure or batching/scheduling too.

• Jul 4

Please @ someone who can review the PR to fix the Embed window sizing, so the games actually look and run nicely inside a post: github.com/forem/forem/pull/23553

Thank you and enjoy the game!

Thoughts sofar? Everyone enjoying the game?

technogamerz profile image

The Lazy Girl

A dreamer working for her dream❤️ Hey everyone! I’m Divyanshi.

Location

INDIA 🇮🇳 Rajasthan kota
Education

Bachelor of Technology (B.Tech.) in Computer Science and Engineering IIT Bombay (2024)
Pronouns

She/her
Work

Microsoft
Joined

Jun 10, 2026

Yes!!

mfenx profile image

Julian Sanders

MFENX builds Power House, a deterministic verification field where computation becomes proof bearing identity, replayable memory, source to fractal execution, and human observable meaning.

Location

San Francisco
Education

Northwestern University
Work

CEO
Joined

Jul 2, 2026

Check out MFENX because its power_house crate turns computational trust into something verifiable, reproducible, and worth serious attention.