henripal
banner
henripal.bsky.social
henripal
@henripal.bsky.social
SotA on MoleculeNet, VP of Morgan Fingerprints.
Hilarious: “The researchers encouraged the struggling machines to persevere, feeding prompts such as “keep working” and “don’t be afraid to execute your code.””

Pathetic: “Despite the exhortations, no model scored above 2% on the test”

www.science.org/content/arti...
‘Brutal’ math test stumps AI but not human experts
Benchmark shows humans can still top machines—but for how much longer?
www.science.org
December 21, 2024 at 5:52 PM
Reposted by henripal
December 10, 2024 at 1:07 PM
Reposted by henripal
Generalizing LLMs to Scientific Applications from Deep Forest Sciences
deepforest.substack.com/p/generalizi...
September 11, 2023 at 7:01 PM