Presented by
BlueDot Impact
We’re building the workforce needed to safely navigate AGI.
Contact: [email protected]
AI Safety Evals - Paper Reading Club
Registration
Past Event
About Event
We are reading:
Monitoring Reasoning Models for Misbehavior and the Risks of Promoting Obfuscation
https://arxiv.org/abs/2503.11926
Every week, someone will present for up to 20 minutes followed by 40 minutes of discussion. RSVP to join or volunteer to present, pick one paper from our suggested list or propose your own.
Presented by
BlueDot Impact
We’re building the workforce needed to safely navigate AGI.
Contact: [email protected]