Inverse Scaling

AI & ML interests

None defined yet.

Recent Activity

aryopg  authored a paper 17 days ago

Beyond Data Filtering: Knowledge Localization for Capability Removal in LLMs

aryopg  authored a paper 17 days ago

The Hot Mess of AI: How Does Misalignment Scale With Model Intelligence and Task Complexity?

haeggee  authored a paper 19 days ago

Training Dynamics of the Cooldown Stage in Warmup-Stable-Decay Learning Rate Scheduler

View all activity

Team members 5