Claude Fable 5.2 Can Do So Much More Than Build Apps
Mark Kashef turns a $99 M5Stack desk robot into a voice-cloned personal assistant by handing the hardware, firmware and debugging loop to Claude.
November 13thCreator
Mark Kashef turns a $99 M5Stack desk robot into a voice-cloned personal assistant by handing the hardware, firmware and debugging loop to Claude.
November 13thMark Kashef shows how to point an uncensored model at your own vibe-coded app to find holes before an attacker does, with three ways to run one: hosted, rented GPU, or your own machine.
October 26thA five-minute walkthrough of the PHP flaw OpenAI helped expose, why older WordPress sites are exposed, and how to check your own site in under two minutes.
October 21stA screen-share essay on auditing a bloated Claude and Codex setup, then rebuilding it around one shared AGENTS.md file and a recurring cleanup habit.
October 17thAn uncensored local model paired with a Ghidra-powered MCP server decompiles QuickTime Player and rebuilds it with the playback controls the frontier models wouldn't touch.
October 12thHow reverse engineering Codex via MCP and automated sub-agent routing turns Claude Code into an autonomous desktop operator.
October 5thA creator built the same voice-and-research app three times, once with each model and once with both, to see where the price gap in OpenAI's new GPT-6.1 Sol actually shows up.
September 30thA practical breakdown of six ways to run Claude Opus 5.5 and Codex's GPT-6 Astra together instead of picking just one.
September 26thTypeSafe's Jev swaps free-form generation for a constrained classifier: give it facts, a question, and the only answers it's allowed to return, and it answers with a confidence score instead of a guess.
September 18thSeven parallel Codex runs, one prompt, six effort levels plus a Sol control: does turning up reasoning effort actually make GPT-6 Astra better, or just slower and more expensive?
September 8thFive ways Mark Kashef points Codex's computer use at apps that have no API, from flight searches to phone settings.
September 5thGrok Bot, Hermes Agent, Claude Cowork, ChatGPT Work, and OpenClaw are all built from the same six parts. The video ranks them twice, then argues the strongest long-term move is skipping all five.
August 23rdA walkthrough of swapping a metered API key for a headless Codex/Claude subscription so internal tools stop billing per click.
August 19thA creator walks through the local tool he built that routes to 37 image and video models, then reverse-engineers exactly what a subscription platform like Higgsfield is doing so you can rebuild it yourself.
August 15thThe same update that let Claude Code and Codex turn a screen recording into a skill quietly taught both of them to watch raw video, no plugin required.
August 8thA Claude Code creator mines his own chat history into a personal test pack, then builds a slash-command benchmark that tells him in one run whether a new model release is actually worth switching to.
July 26thA 44-minute walkthrough of the five-layer stack behind running open-weight AI on your own hardware — and the trick of using Claude Code itself to build the whole thing for you.
July 22ndA breakdown of why maxing out effort settings on Claude, GPT, Grok, and Gemini rarely makes the output better — and the framework for picking the right level every time.
July 13thA 24-minute Earth-layers framework for building AI operating systems that don't decay.
June 30thA 36-minute blueprint for moving a personal AI agent stack into a locked-down, compliance-ready AWS environment — built over a month and nearly 10 million tokens.
June 25thA 9-minute system for mining your JSONL session logs, measuring the behavioral gap between Fable and any other model, and injecting a distilled playbook at every session start.
June 14thA 14-minute cost-routing playbook for the most powerful and expensive model Anthropic has ever shipped.
June 11thSix composable agent patterns from Anthropic's own internal masterclass, with live prompts and honest advice on when to skip workflows entirely.
June 3rdA 12-minute walkthrough of three agentic workflows built around one principle: a second verification pass is what turns a fast answer into one you can trust.
June 1st