Presented by
BlueDot Impact
We’re building the workforce needed to safely navigate AGI.
Contact: [email protected]
AI Safety Evals - Paper Reading Group
Registration
Past Event
About Event
We are reading: Agentic Reinforcement Learning for Search is Unsafe
Read the paper and generate a Q that'll get an excellent A from our presenter/organizer, Mark Keavney and the excellent AI Safety Evals community.
Be sure to check out our website for more information on the AI Safety Evals Group.
Presented by
BlueDot Impact
We’re building the workforce needed to safely navigate AGI.
Contact: [email protected]