What are people actually building with the newest frontier models?

People are building revenue-generating applications with frontier models: automated trading bots ^601,609,102, legal entity setup ¹⁰¹, faceless YouTube channels ^92,467, AI-generated ad creation ^90,210,599, and an OnlyFans persona earning $43,000 in 30 days ¹⁶⁶. 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 ^88,351. Fable 5 is the most cited model, used for complex multi-step tasks ^95,538, autonomous self-improvement ⁹⁸, and rapid game development ^164,311,439. Newer practices include using GPT-5.6 Sol for procedural 3D modeling ¹¹⁶³, solving math problems ¹¹⁶², and generating Minecraft-like games ¹¹⁰⁴; Grok 4.5 for slide decks ¹⁰⁴⁹ and browser tasks ⁹⁹⁴; and local models like Qwen3 for voice assistants ¹¹⁶⁸ and memory systems ¹¹³⁸. Many claims remain emerging with single-source corroboration.[25]

For Fable 5, using /loop for autonomous multi-step work and giving objectives instead of step-by-step instructions yields better results (corroborated by 5 sources) ⁸⁰. Fable 5 can autonomously self-improve and outperform Opus 4.8 on complex tasks at lower cost (corroborated by 15 sources) ⁹⁸. Fable 5 enables rapid full-game development from idea to code in about one hour (corroborated by 4 sources) ¹⁶⁴. 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) ¹⁶⁶. Combining multiple frontier models can automate ad creation from product photos to video (corroborated by 3 sources) ⁹⁰. Using Fable 5 and ClaudeKit's EngineerKit, a single slash command can generate a professional website without a designer or developer (corroborated by 8 sources) ¹⁷¹. Using native Obsidian skills instead of generic HTML parsing reduces context usage by over 99% for AI agents searching vaults (corroborated by 3 sources) ¹⁷⁰. A leaked system prompt can recreate a model's personality on a different base model (corroborated by 2 sources) ⁸⁵. Fable 5 can produce high-quality, animated websites by combining reference screenshots, pre-built components, and specific animation tools with iterative prompting (corroborated by 6 sources) ²⁵⁴. 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) ²⁵². Running Claude Code on an e-ink tablet (reMarkable Paper Pro) creates a distraction-free, eye-comfortable coding environment (corroborated by 2 sources) ²⁴⁶. Claude Opus 4.8 enables reliable autonomous systems that run unattended for hours, using trigger-agent-verification pattern (corroborated by 2 sources) ³⁵⁸. 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) ³⁰⁸. Fable 5 is designed for complex, multi-step tasks that take humans hours or days (corroborated by 3 sources) ⁹⁵. Fable 5 can be given a goal, readiness criteria, and limits to autonomously plan, write, test, fix, and deliver a result (corroborated by 2 sources) ⁵³⁸. Sonnet 5 offers Fable-style agent orchestration at a cheaper tier but may not replace Opus based on testing (corroborated by 2 sources) . Claude Opus 4.8 can generate fully interactive 3D websites from a simple prompt (corroborated by 2 sources) . Different frontier models produce distinct creative outputs when given the same product brief in an agentic pipeline (corroborated by 2 sources) . By adjusting effort, prompts, caching, batching, budgets, and routing, Fable 5 costs can be halved (corroborated by 4 sources) . Fable 5 is free until July 7; use it with Opus 4.8 planning to clone software, audit Claude Code setup, review codebases, or build long-horizon apps (corroborated by 4 sources) . With careful configuration, Qwen3.6-27B at Q8 quantization can achieve near 100K context on 32GB VRAM (corroborated by 3 sources) . Using a frontier model like Fable 5 for planning and reasoning, then delegating execution to cheaper models, yields near-identical results at lower cost (corroborated by 4 sources) . A pipeline combining Claude Opus 4.8 for research, NotebookLM for analysis, and Obsidian for storage can automatically populate a knowledge vault with structured markdown in minutes (corroborated by 2 sources) . Gemini Omni Flash can power a tool that automatically adapts video clips into short-form formats optimized for engagement (corroborated by 3 sources) . Sonnet 5 is designed as a fast, cheap implementer in a multi-agent stack, not a standalone benchmark winner; paired with Fable 5 as advisor, it outperforms solo models (corroborated by 3 sources) . Fable 5 can write, backtest, and deploy a Polymarket arbitrage bot that achieves 98% win rate (corroborated by 2 sources) . Anthropic's free workshops provide a hands-on playbook for building self-improving Claude agents with memory, autonomy, and tool use (corroborated by 2 sources) . A CLAUDE.md file should contain project-specific rules earned from mistakes, not generic advice copied from GitHub (corroborated by 2 sources) . Grok 4.5 can replace Sonnet 5 as an implementer agent in a multi-agent setup, leveraging Grok Build CLI to avoid API fees (corroborated by 2 sources) . Programmers can replace Opus and Sonnet with Grok 4.5 in their systems, achieving 2-3x speed and 50-80% cost reduction (corroborated by 2 sources) . Grok 4.5 is cheapest and fastest but writes more code; Fable 5 produces leanest code but is 22x more expensive (corroborated by 3 sources) . GPT-5.6 Sol as an implementer subagent for Fable achieves superior coding results (corroborated by 2 sources) . GPT-5.6 Sol Ultra produces weaker physics simulations than GPT-5.5 despite higher cost (corroborated by 2 sources) . Qwen 3.6 27B fails in multi-turn agentic workflows due to frequent errors (corroborated by 2 sources) . A Claude-built trading bot using directional market-making can generate significant profit on Polymarket (corroborated by 2 sources) . ClickUp provides 50 free credits to access frontier models without separate subscriptions (corroborated by 2 sources) . A GitHub repo lists permanently free AI APIs with real rate limits, no trials or cards needed (corroborated by 2 sources) . Google DeepMind released Nano Banana 2 Lite, the fastest and cheapest Gemini Image model, and Gemini Omni Flash for video generation and editing (corroborated by 2 sources) .

Key tools and platforms include: Claude Code for autonomous coding and agentic workflows ^{77,101,308,434,990,995}; Cursor with GPT-5.5 or Grok 4.5 for fast development ^600,956; Obsidian for knowledge management ^{163,170,252,475,789,847}; Higgsfield MCP for video and animation ^{249,308,692,749}; ComfyUI for image generation workflows ^91,884; Seedance 2.0 for video generation ^209,474,917; n8n for automation pipelines ⁹²; LangChain for agent building ¹⁰²³; and local inference tools like Ollama ^169,884, llama.cpp ⁵⁰⁵, and llama-swap ⁵⁰⁵. Hardware includes Strix Halo devices for local LLM ^1196,1248, Mac Mini for local pipelines ^169,250, and dual RTX 3090s for 48GB VRAM ²⁵¹.[32]

Several claims are emerging with single-source corroboration and should be treated as unverified: GPT-5.6 Sol underperforms on practical image generation despite strong benchmarks ¹¹³⁶. Fable model is currently too restricted for serious building due to safety filters and metering issues ³⁴⁹. GPT-5.6 Sol on Medium reasoning effort is a good default for coding, upgrade from 5.5 xhigh ¹²⁴². GPT-5.6 Sol can create and edit videos from simple inputs ¹¹⁸⁹. GPT-5.6 can solve previously unsolvable math problems when used by an expert mathematician ¹¹⁹⁰. GPT-5.6 Sol offers reasoning levels from Light to Ultra ¹¹⁹¹. Real-world testing shows GPT 5.6 Soul excels at execution while Fable 5 excels at creativity and strategy ¹¹⁹³. Sol 5.6 is cheaper and token-efficient but weaker on SWE-bench than Fable 5 ¹¹⁹⁴. A USB thumb drive can provide a usable offline LLM knowledge base on any PC with zero setup ¹¹⁹⁷. Tencent's Hunyuan AI model can generate a production-ready landing page with complex UI from a single prompt ¹¹⁹⁸. A single automated loop can replace dozens of saved prompts ¹¹⁹⁹. Using an LLM with tools and a loop (ReAct pattern) can autonomously complete multi-step tasks like trip planning ¹²⁰⁰. Claude Fable 5 can review and fix existing broken workflows ¹²⁰¹. Quants build profitable trading bots by iterating a loop ¹²⁰². A structured decision tree based on task complexity and speed needs helps select the optimal Claude model ¹²⁴⁰. GPT-5.6 Sol and Fable 5 were compared for real work performance with surprising results ¹²⁴³. Following OpenAI's official prompting guide for GPT-5.6 can make the model 10x more efficient ¹²⁴⁴. Combining Grok 4.5 with Hermes and giving it access to tools creates an AI co-founder that is 60% cheaper than Opus 4.8 ¹²⁴⁵. Pre-training a language model on 160GB of 1800s English data and fine-tuning on synthetic Q&A yields a model that can answer historical questions ¹²⁴⁶. Google DeepMind's Antigravity skill allows historians to perform complex AI analysis of inscriptions using plain English . Strix Halo devices can run large models like Qwen 3.6 35B at usable speeds with extremely low power cost . Connecting AI to store memory, competitor data, and a daily decision loop turns an Etsy store into a faster, more focused operation . An agent using the ReAct pattern can autonomously plan a trip by calling tools like search and weather .