Kay Kozaronek

In­vest­ing in Ro­bust Safety Mechanisms is crit­i­cal for re­duc­ing Sys­temic Risks

Search­ing for a model’s con­cepts by their shape – a the­o­ret­i­cal framework

[RFC] Pos­si­ble ways to ex­pand on “Dis­cov­er­ing La­tent Knowl­edge in Lan­guage Models Without Su­per­vi­sion”.

Re­in­force­ment Learn­ing Study Group