Adam Jermyn(Adam Jermyn)

Con­di­tion­ing Pre­dic­tive Models: Open prob­lems, Con­clu­sion, and Appendix

Con­di­tion­ing Pre­dic­tive Models: De­ploy­ment strategy

Con­di­tion­ing Pre­dic­tive Models: In­ter­ac­tions with other approaches

Con­di­tion­ing Pre­dic­tive Models: Mak­ing in­ner al­ign­ment as easy as possible

Con­di­tion­ing Pre­dic­tive Models: The case for competitiveness

Con­di­tion­ing Pre­dic­tive Models: Outer al­ign­ment via care­ful conditioning

Con­di­tion­ing Pre­dic­tive Models: Large lan­guage mod­els as predictors

Un­der­speci­fi­ca­tion of Or­a­cle AI

Multi-Com­po­nent Learn­ing and S-Curves

Eng­ineer­ing Monose­man­tic­ity in Toy Models

Toy Models and Tegum Products

Hu­mans do acausal co­or­di­na­tion all the time

Poly­se­man­tic­ity and Ca­pac­ity in Neu­ral Networks

Smoke with­out fire is scary

It mat­ters when the first sharp left turn happens

Brief Notes on Transformers

Con­di­tion­ing, Prompts, and Fine-Tuning

Con­di­tion­ing Gen­er­a­tive Models with Restrictions

Quan­tiliz­ers and Gen­er­a­tive Models

Grouped Loss may dis­fa­vor dis­con­tin­u­ous capabilities