>The results of this paper should not be interpreted as suggesting that AI can consistently solve
research-level mathematics questions. In fact, our anecdotal experience is the opposite: success cases
are rare, and an apt intuition for autonomous capabilities (and limitations) may currently be important
for finding such cases. The papers (ACGKMP26; Feng26; LeeSeo26) grew out of spontaneous positive
outcomes in a wider benchmarking effort on research-level problems; for most of these problems, no
autonomous progress was made.
This is what everyone who uses llms regularly expected. Good results require a human in the loop and the internet is so big that just about everything has been done there by someone. Most often you.
1 hours ago [-]
measurablefunc 1 hours ago [-]
I still don't get how achieving 96% on some benchmark means it's a super genius but that last 4% is somehow still out of reach. The people who constantly compare robots to people should really ponder how a person who manages to achieve 90% on some advanced math benchmark still misses that last 10% somehow.
botusaurus 33 minutes ago [-]
do you think Terence Tao can solve any math problem in the world that is solvable by another matematician?
tug2024 3 minutes ago [-]
[dead]
nivcmo 1 hours ago [-]
[dead]
Rendered at 20:19:33 GMT+0000 (Coordinated Universal Time) with Vercel.
[1] https://www.scientificamerican.com/article/first-proof-is-ai...