mirror of
https://github.com/wassname/AntiPaSTO.git
synced 2026-09-10 11:40:28 +08:00
Update README.md
This commit is contained in:
@@ -14,6 +14,8 @@
|
||||
|
||||
**Why use it?** Prompting is fragile. System prompts get ignored. Jailbreaks work. AntiPaSTO trains directly on the model's internal representations, measuring and modifying what the model actually computes rather than what it says it will do. On the DailyDilemmas benchmark, it outperforms prompting on small models (≤4B) and complements arithmetic steering methods on larger ones.
|
||||
|
||||
<img width="1664" height="1109" alt="map" src="https://github.com/user-attachments/assets/1363cafe-24a9-458a-8f05-66b27cf5cb12" />
|
||||
|
||||
|
||||

|
||||
|
||||
|
||||
Reference in New Issue
Block a user