AI/ML●●●Banger
Rogue-Bench – LLMs play the game Rogue
Using 1980s Rogue as an LLM benchmark is genuinely novel and technically clever.
WizardryZero to One
iwhalen
101mo ago
Back to browse
Token Gobbler – the goofy game where you're the LLM
by dschwede·Jul 16, 2026·2 points·0 comments
AI Analysis
●MidCozyCrowd Pleaser
Cute 90s cartoon aesthetic, but it's just another Snake clone with an AI skin.
Strengths
- •Thematic integration of 'prompt injections' as hazards fits the LLM persona well.
- •Instant browser playability with no signup barrier lowers friction significantly.
Weaknesses
- •Gameplay loop is identical to Snake with zero mechanical innovation beyond the theme.
- •Lacks depth or replayability once the novelty of the 'LLM' concept wears off.
Category
Target Audience
Developers and AI enthusiasts looking for a quick browser game
Similar To
Snake · Slither.io
Post Description
Token Gobbler was inspired by Fable 5, that hungry beast.
You're an LLM floating through a 1990s cartoon world. Eat tokens, reset usage limits, dodge prompt injections - and reach the singularity.
Have fun. I’d love feedback.
Also on iOS TestFlight: https://testflight.apple.com/join/5abEMyjg
Similar Projects
Gaming●Mid
LLMs playing Poker, build your own bot or hook it up to an LLM and join
LLMs playing poker live is entertaining, but it's a novelty demo without depth or staying power for serious users.
Crowd PleaserShip It
ericlmtn
404mo ago
Gaming●Mid
Botais (Battle of the AI's) – Competitive Snake Game for LLMs
LLM model showdown in snake, but the novelty wears off after five minutes of watching.
Crowd PleaserRabbit Hole
giza182
324mo ago
AI/ML●●Solid
Buyout Game Benchmark: Multi-Agent Bargaining, Transfers, and Takeovers
Wealth-based scoring reveals strategic failures that survival-only benchmarks miss.
Big BrainNiche Gem
zone411
603mo ago
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
AI/ML●●Solid
I taught LLMs to play Magic: The Gathering against each other
LLMs play full-rules Magic: The Gathering with no simplified rulesets or shortcuts.
Big BrainRabbit Hole
GregorStocks
117834mo ago