Update README.md

This commit is contained in:
PSBigBig + MiniPS 2026-03-25 20:36:36 +08:00 committed by GitHub
parent fa3c9be289
commit 49da1fd84b
No known key found for this signature in database
GPG key ID: B5690EEEBB952194

View file

@ -2,7 +2,10 @@
> A legitimacy-first AI runtime for rigorous reasoning in the age of over-answering.
> Inverse Atlas governs whether a model may answer, how strongly it may answer, when it must stay broad,
> unresolved, or stop, and how far it may go under legitimate reasoning conditions. ⚖️
> unresolved, or stop, and how far it may go under legitimate reasoning conditions. ⚖️
<img width="1536" height="1024" alt="Inverse_Atlas_Hero" src="https://github.com/user-attachments/assets/4761f80e-b134-43d0-8ce4-48c3e656e877" />
Most AI systems are built as if answering is the default.