Happy FlexiSpot Black Friday Sale now, Up to 65% OFF! You also have the chance to win free orders during this period. Use my code ”YTE7P50 ” to get EXTRA $50 off on the E7 Plus standing desk.
FlexiSpot E7 Plus standing desk: USA:
CAN:
FlexiSpot Black Friday:
In this video, we will explore the latest research blog Anthropic AI has published discussing about feature steering regarding to mitigate social biases. This is their first step of applying their mechanistic interpretability research to alignment.
Check out my patreon for the research maps!
for existing YouTube members, please DM me on discord
my research paper newsletter
Evaluating feature steering: A case study in mitigating social biases
[Blog]
This video is supported by the kind Patrons & YouTube Members:
🙏Andrew Lescelius, Ben Shaener, Chris LeDoux, Miguilim, Deagan, FiFaŁ, Robert Zawiasa, Marcelo Ferreira, Owen Ingraham, Daddy Wen, Tony Jimenez, Panther Modern, Jake Disco, Demilson Quintao, Penumbraa, Shuhong Chen, Hongbo Men, happi nyuu nyaa, Carol Lo, Mose Sakashita, Miguel, Bandera, Gennaro Schiano, gunwoo, Ravid Freedman, Mert Seftali, Mrityunjay, Richárd Nagyfi, Timo Steiner, Henrik G Sundt, projectAnthony, Brigham Hall, Kyle Hudson, Kalila, Jef Come, Jvari Williams, Tien Tien, BIll Mangrum, owned, Janne Kytölä, SO, Richárd Nagyfi, Hector, Drexon, Claxvii 177th, Inferencer, Michael Brenner, Akkusativ, Oleg Wock, FantomBloth, Thipok Tham, Clayton Ford, Theo, Handenon, Diego Silva, mayssam, Kadhai Pesalam, Tim Schulz, jiye, Anushka, Henrik Sundt
[Discord]
[Twitter]
[Patreon]
[Profile & Banner Art]
[Video Editor] @Booga04
