eringrant.me
Assistant Professor @ualberta.bsky.social & Fellow @amiithinks.bsky.social studying cognition in mind & brain with neural nets, Bayes, and other tools (eringrant.github.io). elsewhere: sigmoid.social/@eringrant, twitter.com/ermgrant @ermgrant
👤 Joined on 23 July 2023
Followers
Following
Total Posts
@eringrant.bsky.social@eringrant.bsky.social → @eringrant.meNot Found
meetfiore.bsky.social
qedscience.bsky.social
Not Found
jurgisbekepuris.bsky.social
icegov.bsky.social
hopea.bsky.social
alfrednobel.bsky.social
jonathanslater.bsky.social
Not Found
Not Found
Not Found
go4know.com
johnegan.bsky.social
inventegy.bsky.social
mostironyalowed.bsky.social
Not Found
Not Found
veblendirectors.bsky.social
getlaunched.bsky.social
murkyconsequences.bsky.social
johntomlinsonfun.bsky.social
Not Found
breckemert.bsky.social
meat-master.bsky.social
Joe Rogan has to pretend he’s not a political actor for his particular politics to appeal to the audience he’s using to accomplish his political goals.
Show PostOur reward function compression work is now out in Nature Communications! 🎉 In it, we present and empirically test a computational framework that formalizes the trade-offs between goal flexibility and learning efficiency. @annecollins.bsky.social @natureportfolio.nature.com doi.org/10.1038/s414...
Show PostReally excited about this paper with @gaiamolinaro.bsky.social - check it out! We have a few other projects coming out soon, which further support the theory we put forward.
Show PostMaybe worth saying aloud that I do worry about safety risks (hacking, bio, an “out of control” agent). I just also see those risks as deeply entangled with money, politics, personalities, regulation, such that I doubt we can “solve safety” if we don’t first address foundational issues.
Show PostThis news is important because all the fucks out there actively attempting to wreck the world want you to think that the work is hopeless and just mitigating the worst case scenario. It's not. Fucking keep going.
Show Post