Pierre Peigné

In­vest­ing in Ro­bust Safety Mechanisms is crit­i­cal for re­duc­ing Sys­temic Risks

Work­shop Re­port: Why cur­rent bench­marks ap­proaches are not suffi­cient for safety?

The Stochas­tic Par­rot Hy­poth­e­sis is de­bat­able for the last gen­er­a­tion of LLMs

Tak­ing fea­tures out of su­per­po­si­tion with sparse au­toen­coders more quickly with in­formed initialization

Clar­ify­ing mesa-optimization

Pierre Peigné′s Shortform