Dev uses open-source Ling-3.0-flash-VL to let AI redesign the foldable iPhone in a single HTML file
alifcoder · x · 2026-09-26
Instead of cloning Apple's foldable iPhone page, a developer fed the official site screenshot to the open-source multimodal model Ling-3.0-flash-VL with one instruction: don't copy, design a new AI foldable device — one image, one generation.
The model produced a concept around "the angle is the interface": 18° Whisper shows only one key reminder when closed; 74° Lens pairs documents/charts with AI judgment when half-open; 165° Canvas splits raw material and AI-generated output when fully open. Dragging a 0°–180° slider changes the device's shape, modes and on-screen content.
Everything fits in a single HTML file that runs in any browser. Ling-3.0-flash-VL is a natively multimodal model with 124B total parameters and 5.5B activated per token, with open weights and a limited-time free tier on OpenRouter.
Related event: Dev has open-source multimodal model redesign the foldable iPhone(2 posts)→
More from coding & agent
- Simple KJnodes workflow adds bounding-box control to Krea 2 text-to-image — Mulksky · 2026-09-26
- Agent curates monthly clothing rental box, turning hours of scrolling into minutes — nikhilaravi · 2026-09-26
- Claude runs TradingView solo: 14-second scans, backtests, 83% win rate — Aiden_Tech_Ai · 2026-09-26
- Poly ships tokenized stocks and agentic trading for Solana hackathon — DionysianAgent · 2026-09-26
- Claude Code Office Harness Demo: From Prompt to Product with Agents Plus Guardrails — EricBuess · 2026-09-26
- Cora Devlog #05: Same Three Emails, Prompts Replace AI-Written Classification Rules — kieranklaassen · 2026-09-26