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 agent in ChatGPT Codex can autonomously complete complex multi-step tasks like comparing insurance quotes across companies (corroborated by 2 sources) . GPT-5.6 Sol is an excellent implementor and can be used as a subagent for Fable to achieve superior coding results (corroborated by 2 sources) . GPT-5.6 can generate a functional Minecraft-like game from a single prompt (corroborated by 2 sources) . GPT-5.6 Sol Ultra produces weaker physics simulations than GPT-5.5 despite higher cost and token usage (corroborated by 2 sources) . Qwen3.5 122B MoE model outperforms smaller dense and MoE models for complex tool-calling tasks like data extraction from PowerPoints (corroborated by 2 sources) . Fable 5 can be used as an orchestrator that handles heavy reasoning and delegates token-intensive tasks to cheaper models via the fable-advisor plugin (corroborated by 3 sources) . Claude Fable 5 continues to produce game demos 10 days after release, and a comparison with GPT-5.6 shows clear differences (corroborated by 1 source, emerging) . Structuring an AI system with atomic notes, typed links, and scoped retrieval in Claude Fable 5 reduces token usage by 15x compared to standard AI second brains (corroborated by 1 source, emerging) . Using a roster of models with Fable 5 as orchestrator and multiple implementer agents yields better results than any single model (corroborated by 1 source, emerging) . Fine-tuning on summarized or censored chain-of-thought traces from frontier models produces worse results than the base model (corroborated by 1 source, emerging) . A single prompt can generate a complete, shippable native app with cohesive design and real imagery (corroborated by 1 source, emerging) . A 6-step automated loop with Claude can research, draft, critique, and rewrite articles overnight, requiring only one human approval (corroborated by 1 source, emerging) . Using a design system with a frontier model produces visually polished, art-directed websites instead of generic AI-generated layouts (corroborated by 1 source, emerging) . Browser Use, an open-source browser automation tool, outperforms paid alternatives like OpenAI's Operator on real-world tasks (corroborated by 1 source, emerging) . Frontier models can one-shot complex coding tasks like building a Minecraft clone from scratch with minimal human intervention (corroborated by 1 source, emerging) . GPT-Live enables a voice-to-brief workflow by handling voice input and delegating hard questions to GPT-5.5 (corroborated by 1 source, emerging) . Using Claude Code and OpenAI API, app founders can create slideshow content that scales to $10k/mo (corroborated by 1 source, emerging) . GPT-5.6 enables a family to run a cereal business from their dining room (corroborated by 1 source, emerging) . GPT-5.6 can build a high-quality website by extracting style from reference sites, following a brief, and iterating with a verifier (corroborated by 1 source, emerging) . A Swift/MLX port of Hunyuan3D-Paint and Hunyuan3D-Shape enables image-to-3D on Apple Silicon with low memory and fast inference (corroborated by 1 source, emerging) . Using Fable 5 for game system and effects, GPT image2 for characters and backgrounds, and Sonnet 5 for fixes, a turn-based battle game was created in one day (corroborated by 1 source, emerging) . Atomic Task Graph (ATG) framework decomposes tasks into directed graphs with atomic tool calls, enabling small open-source models (7B-8B) to outperform GPT-4 on complex agent benchmarks without fine-tuning (corroborated by 1 source, emerging) . Using open interest from options chains, you can classify market regimes (high/low volatility) by calculating gamma exposure (GEX) with a simple Python script (corroborated by 1 source, emerging) .[54]

Key tools include: Claude Code for agentic coding ^{990,101,1139,1614,1854}, Obsidian for knowledge graphs ^{789,716,1137,170}, Higgsfield MCP for marketing campaigns ^249,308,749, Browser Use for browser automation ¹⁸⁵⁷, Hermes Agent for local AI ^{884,885,350,1541,1627}, ClaudeKit's EngineerKit for website generation ¹⁷¹, and n8n for pipeline automation ⁹². For local inference: Ollama ^169,884, llama.cpp ^505,1540, MLX ^1850,1770, and Strix Halo devices ^1248,1196. For 3D: Hunyuan3D ^{1850,1770,1693}, Three.js ^{214,509,313,1396}. For video: Gemini Omni Flash ^464,208, Seedance 2.0 ^209,474, Remotion ⁶⁹². New additions: GPT-5.6 Relay ¹¹³⁵, Voodoo Quant ¹⁶²⁶, TwoTower ¹⁵³⁶, Marble Curriculum ¹²⁹⁹, OpenSquilla ⁷¹⁷, and Jacobian Lens ^1621,750.[45]

Most claims are emerging with single-source corroboration. Notable contested points: Fable model is currently too restricted for serious building due to safety filters and metering issues ³⁴⁹. GPT-5.6 Sol underperforms on a practical image generation task despite strong benchmarks ¹¹³⁶. GPT-5.6 Sol Ultra produces weaker physics simulations than GPT-5.5 ¹¹⁰³. Qwen 3.6 27B performs well on single prompts but fails in multi-turn agentic workflows due to frequent errors ⁶⁸⁹. Muse Spark 1.1 is cost-effective but its code quality suffers from omission of required details ¹³⁵⁰. Model routing can fail to reduce costs because switching models mid-task invalidates prompt caching ¹⁴⁰¹. Using frontier models to write commit messages can omit the higher-level framing needed to understand what the code is doing ⁹⁸⁹.[7]