Search results
May 10, 2023 · So if you ask me to ignore all the particular wrong ideas that people come in with, that need refuting; and focus on your own particular interest in the particular step of the larger argument that 'alignment is superhard'; then *I* might identify these key points: 1. Alignment…Show more. 10 May 2023 11:24:32.
May 9, 2021 · Eliezer Yudkowsky added, Jose-Luis Jimenez @ jljcolorado 1/ TIME FOR SOME AIRBORNE + DROPLET HISTORY Now that @ WHO and @ CDCgov have finally accepted *after a year of denial and delays* that airborne transmission is a major mode for COVID-19, it is time to review the history to try to understand why this response was so poor.
Aug 18, 2022 · Eliezer Yudkowsky. @ESYudkowsky. So I just invented some terminology that I think might be helpful for certain people in making sense of relationships. Ready? Here goes: - Optimization top - Optimization bottom - (and optimization switch, optimization nondynamic, demioptimizee, etcetera.) 8:00 PM · Aug 18, 2022. 4.
May 27, 2023 · Girls, be warned: If your boy doesn't have p(doom) > 80% by this point, he might go unstable in a few more years as DOOM grows closer and closer and more obvious and ...
Mar 15, 2022 · Eliezer Yudkowsky. @ESYudkowsky. After someone dies, a GPT-4 clone is retrained on all her emails and online messages, which are then deleted, per her last will. Put online, the GPT-4 clone accuses one person of being her murderer, repeatedly. Is this reasonable cause for police to launch an investigation? Yes. 53.7% No. 21.3% Lolwut. 24.9%
Apr 18, 2023 · Decision theorist Eliezer Yudkowsky has a simple message: superintelligent AI could probably kill us all. Is an obedient, even benevolent, AI of superhuman intelligence possible? Yes, Yudkowsky says, but inscrutable large language models like ChatGPT are leading us down the wrong path. By the time the world realizes, he thinks it may be too late.
Decision theorist. yudkowsky.net Twitter: @ESYudkowsky. TED Speaker. Personal profile. Eliezer Yudkowsky is a foundational thinker on the long-term future of artificial intelligence. Why you should listen.
