RSS

adityasinha

Karma: 10

Train­ing De­liber­a­tive Mon­i­tors for Black-Box Schem­ing Detection

aksh-n, adityasinha, Victor Gillioz, Simon Storf, Kilian Merkelbach, richbc, Axel Højmark and Marius Hobbhahn
4 Jun 2026 16:43 UTC
32 points
3 comments6 min readLW link