Their "safety" system that arbitrarily flags things. Tons of examples of innocuo... | Hacker News

Hacker Newsnew | past | comments | ask | show | jobs | submit

nijave 16 days ago | parent | context | favorite | on: Claude Tag

Their "safety" system that arbitrarily flags things.

Tons of examples of innocuous strings setting it off and sometimes with financial impact like the OpenClaw/hermes thing (just having the word "hermes" would insta deplete your quota and start charging you API rates in extra usage)

theshrike79 16 days ago [–]

The hermes trigger was a bug and they fixed it in a few hours. But bad news carries far and wide.

nijave 16 days ago | [–]

I read the Github issue. They also initially refused a refund until the whole thing blew up

Here's another one https://github.com/anthropics/claude-code/issues/52809

It's definitely not an isolated incident

Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact