Anthropic studied whether you read permission prompts. You don't. So today it stopped showing them.
The 89% versus 13.6% is real, and it is also the wrong number. Anthropic's own engineering post says the shipped pipeline misses 17% of real overeager actions, Claude's own overreach,, measured on a sample of 52.
"Claude Code's auto mode is safer than human permission review: the classifier caught 89% of planted dangerous commands versus 13.6% for humans, so auto mode becomes the default for paid users on August 14" [SOURCE ↗]
THE CLAIM. auto mode matched or outperformed manual review on every measure Anthropic tested, catching 89% of planted dangerous commands against 13.6% for humans, so from August 14 it is the default for Pro, Max and Team users. THE CHECK: the numbers come from Anthropic's own unreviewed study, the winning comparison is against fatigued humans in a lab scenario, and Anthropic's engineering post calls a different figure 'the honest number': a 17% false-negative rate on real dangerous actions, from a sample of just 52. Anthropic itself still recommends human review for high-risk changes.
Starting August 14, Claude Code sessions on Pro, Max and Team plans default to auto mode. Instead of asking you to approve each command, a classifier reviews every tool call and only interrupts for actions it judges irreversible, destructive, or aimed outside your environment. Enterprise, API and cl
🔒 THE FULL AUTOPSY · FREE WITH AN ACCOUNTYou just read the free check. Sign in free, a code by email, no passwords, and the rest unlocks: the evidence trail, the steelman and the rebuttal, all 4 sources with quotes and screenshots, and our on-record call.
Couldn't verify your access — this looks like our error, not yours.