{"version":1,"type":"story","url":"https://digestai.news/story/developer-trains-12-5m-parameter-ai-to-pick-pokemon-starter-on-single","json":"https://digestai.news/story/developer-trains-12-5m-parameter-ai-to-pick-pokemon-starter-on-single.json","markdown":"https://digestai.news/story/developer-trains-12-5m-parameter-ai-to-pick-pokemon-starter-on-single.md","slug":"developer-trains-12-5m-parameter-ai-to-pick-pokemon-starter-on-single","headline":"Developer trains 12.5M-parameter AI to pick Pokémon starter on single GPU","summary":"A developer named stmonty trained a small AI model with just **12.5 million parameters** on a single **RTX 3080 Ti** to play *Pokémon Red*. The model, built using a **world model** approach inspired by research from Yann LeCun’s AMI Labs, learns button presses by analyzing screen outputs rather than predicting full frames. It compresses visual data into **192 numbers** and uses **reward-free training** initially, with goals introduced later during planning.\n\nThe model required **42,382 grayscale frames** across over **1,000 short runs** to learn basic mechanics. After fine-tuning, it successfully selected **Squirtle** as a starter in **52 out of 100 runs**, outperforming random presses and an untrained model. Stmonty notes compounding errors in predictions as a key challenge. The project, open-sourced on GitHub as *lePokeRed*, demonstrates how lightweight models can tackle niche tasks on consumer hardware. While other approaches have beaten *Pokémon Red* using larger models, this work highlights the potential for hobbyist experimentation.","keyPoints":["Developer stmonty trained a 12.5M-parameter AI on a single RTX 3080 Ti to play *Pokémon Red*,","Model uses compressed screen data (192 numbers) and reward-free training to learn button presses,","After fine-tuning, AI picked Squirtle starter in 52% of 100 runs, outperforming random presses"],"whyItMatters":"Proves small, lightweight models (under 15M parameters) can learn specific tasks on consumer GPUs, opening doors for hobbyist AI experiments and reducing reliance on massive compute.","category":{"slug":"research","name":"Research","url":"https://digestai.news/category/research"},"entities":{"companies":["AMI Labs"],"models":["LeWorldModel","JEPA model"],"people":["stmonty","Yann LeCun"]},"firstPublishedAt":"2026-09-30T11:30:00Z","updatedAt":"2026-09-30T11:30:00Z","sourceCount":1,"hasPrimarySource":false,"sources":[{"outlet":"Tom's Hardware","title":"Developer trains a small AI on a single RTX 3080 Ti gaming GPU to 'play' Pokémon Red","url":"https://tomshardware.com/tech-industry/artificial-intelligence/developer-trains-a-small-ai-on-a-single-rtx-3080-ti-gaming-gpu-to-play-pokemon-red-model-discovered-what-each-button-does-by-predicting-what-happens-next","publishedAt":"2026-09-30T11:30:00Z","type":"press","primary":false,"lead":true}],"sourceNotes":null,"discussions":[],"thread":null,"cite":{"text":"Digest AI, \"Developer trains 12.5M-parameter AI to pick Pokémon starter on single GPU\", 30 September 2026, https://digestai.news/story/developer-trains-12-5m-parameter-ai-to-pick-pokemon-starter-on-single","publisher":"Digest AI","title":"Developer trains 12.5M-parameter AI to pick Pokémon starter on single GPU","datePublished":"2026-09-30T11:30:00Z","url":"https://digestai.news/story/developer-trains-12-5m-parameter-ai-to-pick-pokemon-starter-on-single"},"generatedBy":"Written by Digest AI's editorial model from the linked sources; the sources are the record.","license":"Headlines, digests and key points are written by Digest AI and may be quoted with a link to the story page. Linked articles belong to their publishers. Terms: https://digestai.news/terms#reuse"}