Jeffrey Ladish

Bounty for Ev­i­dence on Some of Pal­isade Re­search’s Beliefs

Take SCIFs, it’s dan­ger­ous to go alone

Pal­isade is hiring Re­search Engineers

unRLHF—Effi­ciently un­do­ing LLM safeguards

LoRA Fine-tun­ing Effi­ciently Un­does Safety Train­ing from Llama 2-Chat 70B

The Agency Overhang

Dona­tion offsets for ChatGPT Plus subscriptions

To de­ter­mine al­ign­ment difficulty, we need to know the ab­solute difficulty of al­ign­ment generalization

Thoughts on the OpenAI al­ign­ment plan: will AI re­search as­sis­tants be net-pos­i­tive for AI ex­is­ten­tial risk?

AGI sys­tems & hu­mans will both need to solve the al­ign­ment problem

When you plan ac­cord­ing to your AI timelines, should you put more weight on the me­dian fu­ture, or the me­dian fu­ture | even­tual AI al­ign­ment suc­cess? ⚖️

Mar­riage, the Giv­ing What We Can Pledge, and the dam­age caused by vague pub­lic commitments

My vi­sion of a good fu­ture, part I

In­for­ma­tion se­cu­rity con­sid­er­a­tions for AI and the long term future

Don’t die with dig­nity; in­stead play to your outs

EA Han­gout Pri­son­ers’ Dilemma

Com­ment on the lab leak hypothesis

Nu­clear war is un­likely to cause hu­man extinction

Was SARS-CoV-2 ac­tu­ally pre­sent in March 2019 wastew­a­ter sam­ples?

land­fish lab