Four Claude models, a 10x price spread, and a default recommendation that is not the most expensive one. The selection guide also says tuning effort beats switching models.
A PreToolUse hook that blocks rm -rf took ten minutes to write and caught 2 of 6 ways to delete a directory. Worse, it failed open: broken, it exited 0 and let the delete through.
An audit of 77 Claude Code rule files found 22 loading on every session, and 10 of those were Chinese translations of the other 10. That is 4,265 tokens of duplicate instruction per session.
DoltLite reached beta on about 2,000 AI agent pull requests. We counted its divergence files ourselves: 4,705 classified entries, and exactly one is a real bug.
A published inventory of ChatGPT Work lists 232 tool interfaces, 44 skills and 615,000 characters of skill source. Its browser skill deliberately withholds its own instructions, and the reason is arithmetic.
Claude Code budgets its skill listing at 1 percent of the context window. We counted 228 skills across four scopes totalling 50,606 characters, 25 times over budget on a 200K model.
A story about Apple being surprised by AI demand drew 386 comments, and the top one called it marketing. We checked: the same publication ran the same headline shape in May.
Install takes two minutes. The part worth learning is skills, and the guides skip it. Six of them now produce this site: 5 articles, 6,883 words, and 2 mistakes that cost us an afternoon.
Delisted from the Web Store on 31 August, ending a phase-out that began in June. 476 points and 379 comments in a day, and the argument was not the one you would expect.
The filter is 377 lines and one regex over YouTube's own badge, so it is exactly as good as YouTube's labeling policy and no better.
The strongest version of the case that the taxonomy argument is beside the point.
We tested this claim ourselves. Module shadowing fires by default and one flag stops it, except on the macOS system Python.