The prompt behind making text-only LLMs draw 16×16 pixel images
gabriberton · x · 2026-10-26
gabriberton published the prompt used to make vision-free, text-only LLMs draw in pure text: output exactly 16 lines of 16 digits (0 black, 1 white), with scaffolding to recall how the subject is usually drawn in icons, lay out parts with rough x/y coordinates, draft the grid, then re-read row by row and fix what looks wrong.
Each concept was drawn 5 times per model, keeping the best result; any model trained with vision (e.g. Gemma 4) was excluded to test whether pure language models can render objects they never saw.
Related event: Text-only LLMs can draw pixel art without any vision training(3 posts)→
More from Models
- yacine claims OpenAI models have allowed 'borderline and dangerous' tasks since codex 5.4 — yacineMTB · 2026-10-26
- Block unveils Dessa, a full-duplex speech model trained only on human conversation — daluoseo · 2026-10-26
- DeepSeek V4.1F tops Chinese models on FrontierMath Tier 4 at 46% — teortaxesTex · 2026-10-26
- Casado slams Claude's safety classifier for flagging 'fetching my own documents' as reasoning extraction — AccBalanced · 2026-10-26
- Yacine MTB: DeepSeek is 'undoubtedly' a frontier model — yacineMTB · 2026-10-26
- Single-neuron steering: injecting a "joyful neuron" visibly alters a model's self-description — Sauers_ · 2026-10-26