A proper guide to Fable 5
How Theo turned a returned, unmetered Claude release into a five-and-a-half-hour unattended agent run that cleared a month of stalled pull requests for about $150.
July 6thCreator
How Theo turned a returned, unmetered Claude release into a five-and-a-half-hour unattended agent run that cleared a month of stalled pull requests for about $150.
July 6thA 23-minute rebuttal of three viral claims about Anthropic's returning Fable model — that it's nerfed, that its subscription pricing is a bait-and-switch, and that it's too expensive to run.
July 4thA Mac loyalist explains why agentic coding broke macOS for him -- and how a fleet of $400 Linux mini-PCs fixed it.
July 3rdA 28-minute benchmark teardown of Claude Sonnet 5, plus the government letter that brought Fable back from the dead.
July 1stOpenAI's next-generation model family exists, benchmarks impressively, and is locked behind a US government approval gate — a 30-minute breakdown of what that means.
June 27thA 20-minute investigation into the US government export control that pulled Anthropic's two best AI models offline — and what that precedent means for every developer who builds on frontier AI.
June 24thA 44-minute wishlist from a burned-out builder who wants solo devs to tackle the infrastructure problems that have gone unsolved for a decade.
June 22ndA 25-minute case for letting agents run their own loops — and how one 2:29 AM prompt produced four merged PRs by morning.
June 18thA reluctant 28-minute tour of the Claude Code features every competing harness should steal.
June 17thTheo breaks down how Anthropic silently modified prompts, rewrote its system card, and built invisible safeguards into its most capable model - then got caught.
June 15thA live 14-minute breakdown of the US government export control directive that forced Anthropic to pull Fable 5 and Mythos 5 offline for all non-US citizens — including Anthropic's own employees.
June 13thA 30-minute field report on burning $5,400 of subsidized AI inference in ten days — and what actually came out of it.
June 12thA 33-minute first-take from a developer who spent $3,000 on inference in 24 hours — benchmarks, real demos, session math, and the hidden safety intervention that silently degrades the model without telling you.
June 11thA 23-minute supply-chain autopsy explaining why Elon's reckless GPU overbuy is now the most valuable compute position in the world.
June 9thTheo scraps cursor, plan mode, and Claude after five months — here is exactly what replaced them.
May 27thTheo goes all-in on Claude Code over the holiday break — six parallel instances, no IDE opened, two projects from scratch — and comes back with a changed worldview on writing code.
January 6th