AI
Fable 5 Is Back, and It Wrote This Post
The export controls came off June 30 and Fable 5 returned July 1 — with a stricter classifier and a standing government role in future Anthropic releases.
Claude Code
AI
Claude Sonnet 5: Near-Opus Performance, Sonnet Pricing
Claude Sonnet 5 launches today at well under half of Opus 4.8's price. Benchmarks, context window, and safety findings from the official system card.
AI
Anthropic Gave Me $3,959.78 of Claude Code Use for $200
I spend $200 a month for Claude's Max plan and lean on it every day. I metered 30 days of that work at Anthropic's own API rates: $3,959.78 — a near twenty-to-one discount, and probably the cheapest frontier-AI access of the foreseeable future.
AI
Google's Open Knowledge Format, and the Plugin I Built for It
Google released Open Knowledge Format, a plain-Markdown way to give AI agents your institutional knowledge. I read the spec and built a Claude Code plugin and skill for it.
AI
I Built My First Claude Code Skill: An Email Client
I had Claude build my first skill — an email client for my AI coding tools. The tool is handy; the real lesson is that you can teach these tools almost anything.
AI
Fable 5 Was Nice While It Lasted
The government made Anthropic pull Fable 5 and Mythos 5 for everyone, over a jailbreak that amounts to asking a model to fix bugs in code. The facts, and why it hit me personally.
AI
Two Days of Phone Troubleshooting. Claude Code Needed 15 Minutes.
Five users couldn't reliably hear callers on their softphones, and a day and a half of conventional troubleshooting pinned it to their PCs without explaining it. I pointed Claude Code at a broken machine and a working one. Fifteen minutes later it had the root cause, the fix, and two bonus findings.
AI
I Tripped Fable 5's Safety Guardrails on Day Two
Two days into the Fable 5 window, a binary export of blank mammography templates tripped Anthropic's new safety classifiers — cybersecurity and biology at once. Then writing this post tripped them again. Both times, the quiet handoff to Opus 4.8 worked exactly as advertised.
AI
An AI Probably Approved Me to Research Vulnerabilities
Claude blocked a routine web search about an npm vulnerability and pointed me to Anthropic's Cyber Verification Program. I applied out of curiosity — and the approval came back so fast that a human almost certainly never read it.
AI
What a $200 Claude Max Plan Really Buys: I'm Nearing $3,000 in Value
I've spent the better part of a year wondering whether my flat $200 Claude Max plan was a bargain or a rip-off. So I built a tool to meter my Claude Code usage across four machines — one ordinary week billed out at $737 by API pricing.