libraryjenn.bsky.social
Neurospicy librarian; Doctoral hopeful (Simmons ‘30); Olympic hopeful (Brisbane ‘32). Lazy, but bad at it. DM policy: include your reason in your FIRST message. Content: obscure primary sources, #ALA. Mocking my horse, #GarbageMare.
👤 Joined on 14 November 2024
Followers
Following
Total Posts
@libraryjenn.bsky.socialthetnholler.bsky.social
usatodayopinion.usatoday.com
rowdiestuncle.bsky.social
lizval.bsky.social
vivien3daggers.bsky.social
sammiestsam.sheshed.rocks
emlieb.bsky.social
invaderpou.bsky.social
fkftsh.myatproto.social
renleve.bsky.social
tetrags.bsky.social
mattsteinglass.bsky.social
jacobmsmall.bsky.social
Not Found
go4know.com
Not Found
nlthorsen.bsky.social
dani711.bsky.social
stoneheart314.bsky.social
darkelfontheshelf.bsky.social
Not Found
kamala-got-smoked.bsky.social
Not Found
ranchoapocalypto.bsky.social
riendeplus.bsky.social
Pepper was actually the name of the doctor, not the monster
Show PostYou may save money in the short term, at the expense of worse work at the end. That doesn't mean small models can't do tons of valuable work, but you want to make sure they are orchestrated and error-checked by larger ones for many kinds of tasks. Paper: arxiv.org/pdf/2509.09677
Show PostThis paper shows why I am skeptical of the idea that frontier models can be easily replaced by cheaper ones (and why you should use the best models as orchestrators): Small improvements in accuracy & judgement compound over long-horizon tasks, creating huge gains in outcomes and reduction in errors.
Show Post🙄 Glaciers around the world are shrinking and losing mass at an accelerating rate due to rising global temperatures, low winter snowfall, and intense summer heatwaves
Show Post