Gemini 4 Argon demos: 1M-token city build, paper-to-neural-net training, screenshot site rebuilds
Prompt Engineering · youtube · 2026-10-14
Prompt Engineering got early access to Gemini 4 Argon for a couple of weeks and shared standout demos:
- An entire coastal city in one response: the model generated a full coastal city within a single 1-million-token output
- Paper to neural network: trained a neural network from scratch on a DGX Spark using only a research paper
- Screenshot-to-website: rebuilt websites from a screenshot without using a single image file
The full video covers every demo and where each one broke.
Related event: Gemini 4 Argon early access: creators demo million-token outputs(14 posts)→
More from coding & agent
- Bun ships bun lint: 26x faster ESLint-compatible linter; Oxlint creator unimpressed — cnakazawa · 2026-10-15
- REA 'Reverse Engineer Anything' tops GitHub trending, letting Claude Code and Codex decompile any app — blaizedsouza · 2026-10-15
- REA v6.5 ships with 529 PRs from 200+ contributors, adding offline evidence inspection and JS bundle recovery — blaizedsouza · 2026-10-15
- Cline: Gemini 4 Argon saw 3x Claude's day-one adoption and 30% fewer tokens — JMateosGarcia · 2026-10-15
- Codex Mac app hit 5M weekly users in 4 months, then became the ChatGPT app — every · 2026-10-15
- AI coding agents on production codebases: 4 setups tried, 3 failed, one workflow stuck — paulabartabajo_ · 2026-10-15