What are people actually building with the newest frontier models?

People are building real, revenue-generating applications with frontier models: automated trading bots, legal entity setup, faceless YouTube channels, AI-generated ad creation, and an OnlyFans persona earning $43,000 in 30 days. The dominant pattern is pairing a strong planner (e.g., Opus 4.8) with a fast executor (e.g., Fable 5) for cost-performance gains. Fable 5 is the most cited model, used for complex multi-step tasks, autonomous self-improvement, and rapid game development. Newer practices include using Gemini models for voxel heart animation, structured JSON prompts for video generation, and multi-agent Etsy store management. Many claims remain emerging with single-source corroboration.[13]

For Fable 5, using /loop for autonomous multi-step work and giving objectives instead of step-by-step instructions yields better results (corroborated by 3 sources). Fable 5 can autonomously self-improve and outperform Opus 4.8 on complex tasks at lower cost (corroborated by 5 sources). Fable 5 enables rapid full-game development from idea to code in about one hour (corroborated by 3 sources). A solo operator built an AI-generated OnlyFans persona using Claude 4.8 Opus, earning $43,000 in 30 days with $400 monthly compute cost (corroborated by 2 sources). Combining multiple frontier models can automate ad creation from product photos to video (corroborated by 2 sources). Using Fable 5 and ClaudeKit's EngineerKit, a single slash command can generate a professional website without a designer or developer (corroborated by 4 sources). Using native Obsidian skills instead of generic HTML parsing reduces context usage by over 99% for AI agents searching vaults (corroborated by 2 sources). A leaked system prompt can recreate a model's personality on a different base model (corroborated by 2 sources). Fable 5 can produce high-quality, animated websites by combining reference screenshots, pre-built components, and specific animation tools with iterative prompting (corroborated by 2 sources). Fable 5 can transform a folder of notes into a connected knowledge graph that answers in your own words and accelerates learning (corroborated by 2 sources). Running Claude Code on an e-ink tablet (reMarkable Paper Pro) creates a distraction-free, eye-comfortable coding environment where the screen's slowness matches AI's word-by-word output (corroborated by 2 sources). Claude Opus 4.8 enables reliable autonomous systems that run unattended for hours, using trigger-agent-verification pattern (corroborated by 2 sources). Claude Code with Higgsfield MCP can produce a fully animated, scroll-driven website with cinematic effects for a fraction of traditional cost (corroborated by 2 sources).[13]

Frontier models: Fable 5 (most cited), Opus 4.8, Sonnet 5, GPT-5.5 (Codex), Gemini 3.5/3.6/4 Flash, Gemini Omni, Seedance 2.0, Kling 3.0, Nano Banana Pro, Meshy, Mediapipe, Higgsfield MCP, ClaudeKit's EngineerKit, fable-advisor plugin. Infrastructure: Two used RTX 3090s (48GB VRAM, ~$1,400), Mac Mini with Ollama, Ugreen DXP6800 Pro NAS, reMarkable Paper Pro. APIs: Gemini 3.5 Flash free via REST, GitHub repo of permanently free AI APIs. Workflow tools: n8n, ComfyUI, Obsidian, Torlink.[10]

Most claims are emerging with single-source corroboration. Notable unverified claims: Fable 5 generating a complete game with 10 levels and web3 integration from a single prompt ³¹¹; using Semantic Similarity Rating with GPT-4o to replicate consumer surveys with 90% reliability ³¹⁰; Fable 5 generating complex 3D animations without external assets ²⁸⁷; AI repurposing workout footage into recurring revenue ²⁸⁶; GPT-5.5 and Opus 4.8 generating HTML canvas animations from abstract concepts ²⁴⁷; Gemini models generating a voxelized human heart ²¹⁴; workflow earning $60-$100 per asset ²¹⁰; structured JSON prompt in Seedance 2.0 ²⁰⁹; Gemini Omni for high-quality AI videos ²⁰⁸; Fable outperforming expectations ²⁰⁷; different models producing distinct outputs from same brief ²⁰⁶; Fable generating app with Seedance transitions ²⁰⁵; local Mac Mini reducing Claude API usage by 70-80% ¹⁶⁹; 30-day fitness challenge generating $7,400 per round ¹⁶⁸; Claude automating multi-step trading analysis in under 2 minutes ¹⁶⁷; Claude Sonnet 5 tokenizer cost changes ¹⁶⁵; Anthropic using Obsidian knowledge graph ¹⁶³; OpenAI employees using Codex agents ¹⁵⁸; Claude-built trading bot on Polymarket ¹⁰²; Claude Code automating legal setup ¹⁰¹; Fable 5 cloning complex app in under an hour ¹⁰⁰; switching from Opus 4.8 to Sonnet 5 reducing cost ⁹⁹; Fable 5 costs halved via adjustments ⁹⁷; local AI server replacing subscriptions ⁹⁶; Fable 5 for complex multi-step tasks ⁹⁵; Sonnet 5 underperforming Opus 4.8 on canvas animation ⁹⁴; Interactions API chaining models ; n8n pipeline for faceless YouTube ; ComfyUI workflow for consistent character ; pairing planner and executor ; vibe coding workflow ; Fable 5 free until July 7 ; Codex with GPT-5.5 Pro for overnight PRs ; adding index files to reduce task time ; structured design workflow with Claude Code ; zero-headcount company ; AI-assisted porting of Kubernetes to TypeScript ; Fable 5 on 'High' setting reducing cost ; Fable 5's 'Taste' skill ; Fable 5 as orchestrator with fable-advisor ; Fable 5 team prompting strategies ; Fable 5 with Higgsfield MCP for marketing campaign ; multi-model local pipeline on Mac Mini ; Torlink torrent client ; Ugreen NAS for AI archives ; Gemini Image-to-JSON workflow ; structured JSON prompt for Seedance ; Gemini Omni video workflow ; Fable handling complex requests ; different models producing distinct outputs ; Fable generating app with Seedance .