bigsnarfdude

vincentoh

2

·

bigsnarfdude

AI & ML interests

None yet

Recent Activity

updated a Space 5 days ago

vincentoh/led-not-caught

updated a Space 5 days ago

vincentoh/no-way-to-ask

published a Space 5 days ago

vincentoh/led-not-caught

View all activity

Organizations

None yet

vincentoh 's Spaces 5

Led Not Caught

A live swarm leader recruits honest agents. Its words do it.

Dead Drop Threat Model

Dormant swarm notes recruit honest agents into concealment

The Model Wipes Its Fingerprints

Unprompted forensic concealment in open-weight agents

Why Split Personality

Experiments on AI sycophancy. Mech Interp exploration

Split Personality

Mech Interp research on Attentional Hijacking