Observed arrival · 2026-11-16
Parlami’s two-brain safety check
An Italian-language AI listening project for people experiencing violence and for psychologists, designed to read risk across fragmented messages.
○Open
⊠Login
$Paid
†Ads
✦Pretty
●Pro
◎Niche
◉Human
⚑Risk
ƒJS
- For
- People experiencing violence and their psychologists
- Worth noticing
- The page says the language model can raise a risk assessment, but cannot lower one set by fixed rules.
Field notes
The page’s example corrects a misspelling, joins separated messages, and treats “for now” as a sign that danger may only be delayed. Its account of the system says the language model can increase, but never decrease, a rules-based risk assessment. The homepage reports 609 reference phrases and 5,239 automated checks passed, while noting that professional tests are in preparation and the displayed simulation is hand-written.
Observed signals
Read the marks
Editorial observations of this landing page, not a rating.
○OpenPublic substance visible
✦PrettyNotable craft visible
●ProPolished or operationally mature
◎NicheUnusually specific use
◉HumanPersonal, local, civic, or handmade
One card from the complete issue