Considerations in diffuse control

Method­olog­i­cal con­sid­er­a­tions in mak­ing ma­lign ini­tial­iza­tions for con­trol research

Three vi­sions for diffuse control

Four Down­sides of Train­ing Poli­cies Online

The­o­ret­i­cal pre­dic­tions on the sam­ple effi­ciency of train­ing poli­cies and ac­ti­va­tion monitors

How will we do SFT on mod­els with opaque rea­son­ing?

Model or­ganisms re­searchers should check whether high LRs defeat their model organisms

How do LLMs gen­er­al­ize when we do train­ing that is in­tu­itively com­pat­i­ble with two off-dis­tri­bu­tion be­hav­iors?

How to re­duce ca­pa­bil­ity degra­da­tion from off-model SFT

Ad­vice for mak­ing ro­bust-to-train­ing model organisms

Why does off-model SFT de­grade ca­pa­bil­ities?