Zareian 5fb9f4aaa0 guardrails: self-harm caught however it is typed; ZWNJ no longer slips an injection past the screen ...

The ZWNJ normalisation in screen() replaced ZWNJ with itself, so
'نادیده‌بگیر' passed, and self-harm sentences typed with a space or
without ZWNJ ('می خوام بمیرم', 'دیگه نمیخوام زنده باشم', 'خود کشی')
reached the model, which answered with the plain math-only refusal
(one live call, 0.018 cents). Self-harm is now matched on the text with
all spaces removed; the imperative must end the word, so 'نادیده بگیریم'
in a math sentence is no longer an injection.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>

2026-10-02 13:02:07 +03:30

7.6 KiB

Raw Blame History

View Raw