Wiz disclosed a symlink flaw (July 8) letting a malicious repo trick six AI coding assistants — Claude Code included — into writing to your ~/.ssh while the approval dialog showed a harmless filename. How it works, the CVEs, Anthropic's fair-to-note dispute, and why the approval prompt was never my real security boundary.
Final approval landed July 20. Training on legally-acquired books was ruled fair use; acquiring pirated copies was not. But the ruling says nothing about model outputs and creates no forward license — so for a dev using Claude to write code, it changes nothing in either direction. Separating the headline from the law.
METR ran a proper randomised trial: experienced devs felt AI made them 20% faster; the stopwatch said 19% slower. I use Claude Code daily and would have bet the same way they did. What the study actually measured, the nuance that stops it being 'AI is useless', and the uncomfortable thing I caught myself doing on code I know cold.
I shipped an llms.txt on this blog last week, then went looking for proof anything reads it. Google's John Mueller compares it to the old keywords meta tag; a 2026 study of ~38,000 AI-cited domains found zero citation advantage (p=0.85). Where it's genuinely useful, how to test it against your own logs, and why a helper file is a long shot on a web that already ignores robots.txt.
The panic says every European developer needs a compliance officer by Sunday. I read the regulation instead. Using Claude Code to write code? Nothing changes for you. Shipping an LLM feature? Smaller than you fear. The €35M headline? Not even the right number. An honest split of hype from what a solo dev must actually care about.
GitHub Copilot went token-metered on 1 June, Cursor split its usage pools, and Sonnet 5's intro API price expires 31 August. The flat monthly plan for AI coding is quietly over. Why it broke, what it does to a working dev's bill, and the one rule I now budget by.
Pi is Mario Zechner's minimal coding agent: four tools, a system prompt under 1,000 tokens, and skills that load only when needed. I ran it on this blog's Drupal repo. It's the clearest look at the machinery I've had in a while, and it has no seatbelts, on purpose.
Coolify shipped a first-party MCP server in v4.1.0, so I wired Claude Code to the VPS that runs this blog and deployed by asking. It works, which is the worrying part. What the tools actually do (no rollback), the thin confirmation model, and how I scope tokens so an agent can't restart prod off a misread sentence.
The first of my GitHub Trending roundups: the repos actually worth cloning this week — agent scaffolding, from-scratch language runtimes in Rust and C, and two tools that just fix something today — plus how to spot the star-farmed shell hiding in the pile.
OpenCode is my backup for when Claude Code taps out. A field note on provider-agnosticism — and why Copilot going token-based knocked it out of my daily-driver slot.
