//
sign in
Profile
by @danabra.mov
Profile
by @dansshadow.bsky.social
Profile
by @jimpick.com
AviHandle
by @danabra.mov
AviHandle
by @dansshadow.bsky.social
AviHandle
by @katherine.computer
EventsList
by @katherine.computer
ProfileHeader
by @dansshadow.bsky.social
ProfileHeader
by @danabra.mov
ProfileMedia
by @danabra.mov
ProfilePlays
by @danabra.mov
ProfilePosts
by @danabra.mov
ProfilePosts
by @dansshadow.bsky.social
ProfileReplies
by @danabra.mov
Record
by @atsui.org
Skircle
by @danabra.mov
StreamPlacePlaylist
by @katherine.computer
+ new component
Profile
Loading...
Writes about cognitive science and philosophy. Professes psychology at Princeton University. Devours chocolate and fiction. www.tanialombrozo.com
Tania Lombrozo








Loading...
Specifying S and T are not only important for clarity and precision, but for pinning down the relevant notion of understanding. Some accounts of understanding suggest that understanding a *person*, for example, is very different from understanding math or science or language.
Our paper draws on philosophy and the cognitive sciences, including psychology, education, and AI. This is reflected in our authorship team - possibly the most interdisciplinary of my career! We span psychology, philosophy, computer science, and HCI.
Our aim in the paper isn't to argue for a particular account of understanding, but to offer a landscape of options. Clarifying machine understanding (and how to assess it!) is important for both AI safety and for creating more human-like forms of artificial intelligence.
We're grateful to a large number of people for helpful conversations and feedback in developing this project, including (but not limited to)...
14d
14d
14d
14d